Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-10T11:58:37.331025Z
Paper Citation Record · LEDGER
Sparse Autoencoders Trained on the Same Data Learn Different Features
As of 21 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 30 inbound Pith citation observations for arXiv:2501.16615.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-16T12:29:34.117929Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
26 of 26 outbound references displayed
- verified exact0
- verified fuzzy6
- unresolved20
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 4ec5f24a-3453-4ded-bb68-8820c0bcd3eb · outbound
This paper cites write newline.
Sparse Autoencoders Trained on the Same Data Learn Different Features write newline
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:36.899951Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fa931dab-10f2-4acf-96aa-bf59dd4bc20d · outbound
This paper cites write newline.
Sparse Autoencoders Trained on the Same Data Learn Different Features write newline
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:36.936293Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eca188c6-ca03-493b-97ad-9168a85834a0 · outbound
This paper cites Git re-basin: Merging models modulo permutation symmetries.
Sparse Autoencoders Trained on the Same Data Learn Different Features Git re-basin: Merging models modulo permutation symmetries
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T11:58:37.811691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 6b025c49-dd4c-4b70-b9f1-cdbb6e481606 · outbound
This paper cites Sparse autoencoders do not find canonical units of analysis.
Sparse Autoencoders Trained on the Same Data Learn Different Features Sparse autoencoders do not find canonical units of analysis
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T11:58:37.803757Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation afd0de54-4380-40cc-98b4-661fbb1fa857 · outbound
This paper cites Linear algebraic structure of word senses, with applications to polysemy.
Sparse Autoencoders Trained on the Same Data Learn Different Features Linear algebraic structure of word senses, with applications to polysemy
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.020986Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ebebd8f-f61d-4f70-9ddb-fa83f7df0cff · outbound
This paper cites Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs.
Sparse Autoencoders Trained on the Same Data Learn Different Features Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.031801Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff3d2ade-f299-44de-ad91-82db002abc82 · outbound
This paper cites Mechanistic Permutability: Match Features Across Layers.
Sparse Autoencoders Trained on the Same Data Learn Different Features Mechanistic Permutability: Match Features Across Layers
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.035849Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5bf976c2-bfac-45ce-88f3-e2153da84431 · outbound
This paper cites Sae repository.
Sparse Autoencoders Trained on the Same Data Learn Different Features Sae repository
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T11:58:37.790457Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 2397883a-6002-4f83-afae-c767ced785a7 · outbound
This paper cites G., Bradley, H., O’Brien, K., Hallahan, E., Khan, M.
Sparse Autoencoders Trained on the Same Data Learn Different Features G., Bradley, H., O’Brien, K., Hallahan, E., Khan, M
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.041431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 02bf38a3-4166-4844-9a19-177480580936 · outbound
This paper cites Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning.
Sparse Autoencoders Trained on the Same Data Learn Different Features Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.044442Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 91109b86-a059-4d91-8816-b545eaad387b · outbound
This paper cites L., Anil, C., Denison, C., Askell, A., Lasenby, R., Wu, Y., Kravec, S., Schiefer, N., Maxwell, T., Joseph, N., Tamkin, A., Nguyen, K., McLean, B., Burke, J.
Sparse Autoencoders Trained on the Same Data Learn Different Features L., Anil, C., Denison, C., Askell, A., Lasenby, R., Wu, Y., Kravec, S., Schiefer, N., Maxwell, T., Joseph, N., Tamkin, A., Nguyen, K., McLean, B., Burke, J
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T11:58:37.778055Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 8911dae6-91d5-499a-a5cc-36fe7d4080ee · outbound
This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoencoders.
Sparse Autoencoders Trained on the Same Data Learn Different Features A is for absorption: Studying feature splitting and absorption in sparse autoencoders
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.050861Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6fef1f70-6c20-4d81-9308-db0ea5683aa6 · outbound
This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.
Sparse Autoencoders Trained on the Same Data Learn Different Features Sparse Autoencoders Find Highly Interpretable Features in Language Models
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.053885Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cabaa19-cb66-4db0-89af-17c70301a7ac · outbound
This paper cites The Llama 3 Herd of Models.
Sparse Autoencoders Trained on the Same Data Learn Different Features The Llama 3 Herd of Models
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.056854Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2e47b8e9-422b-4a69-a7c0-2e077293fadc · outbound
This paper cites Toy Models of Superposition.
Sparse Autoencoders Trained on the Same Data Learn Different Features Toy Models of Superposition
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.060199Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f1ef7e34-c91d-4568-bb8a-66a4bfb724d0 · outbound
This paper cites Not All Language Model Features Are One-Dimensionally Linear.
Sparse Autoencoders Trained on the Same Data Learn Different Features Not All Language Model Features Are One-Dimensionally Linear
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.064303Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2d23deb-61b9-4bf0-b8a8-6ca19d5d3463 · outbound
This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.
Sparse Autoencoders Trained on the Same Data Learn Different Features The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.066893Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 455e172a-946d-407c-b4cd-e54d5308e024 · outbound
This paper cites Scaling and evaluating sparse autoencoders.
Sparse Autoencoders Trained on the Same Data Learn Different Features Scaling and evaluating sparse autoencoders
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.070778Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba99b6ad-223a-498a-a90a-b8aaa4cb18bb · outbound
This paper cites Saebench: A comprehensive benchmark for sparse autoencoders, 2024.
Sparse Autoencoders Trained on the Same Data Learn Different Features Saebench: A comprehensive benchmark for sparse autoencoders, 2024
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.074327Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6d8fbe5-0347-4fd7-b6d7-14cc6fe30d10 · outbound
This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.
Sparse Autoencoders Trained on the Same Data Learn Different Features Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.077293Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 063649c0-073b-4168-9ff4-7c7b39ebdca7 · outbound
This paper cites Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders.
Sparse Autoencoders Trained on the Same Data Learn Different Features Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.080957Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 609ea754-a9c9-4872-bdf8-5198463299df · outbound
This paper cites Interpretability dreams.
Sparse Autoencoders Trained on the Same Data Learn Different Features Interpretability dreams
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T11:58:37.764140Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 5b5e109b-dc60-434f-b6d1-9e38a1c46758 · outbound
This paper cites Automatically Interpreting Millions of Features in Large Language Models.
Sparse Autoencoders Trained on the Same Data Learn Different Features Automatically Interpreting Millions of Features in Large Language Models
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.143219Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b0a12e3f-ebc3-4ecd-8753-f07a8c7dcc1d · outbound
This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.
Sparse Autoencoders Trained on the Same Data Learn Different Features Improving Dictionary Learning with Gated Sparse Autoencoders
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.188840Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c16a6c4c-1da4-4041-85aa-d6abac9e8b0f · outbound
This paper cites The strong feature hypothesis could be wrong, 2024.
Sparse Autoencoders Trained on the Same Data Learn Different Features The strong feature hypothesis could be wrong, 2024
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T11:58:37.756045Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 76947b42-accf-4ad1-a014-ae26b5c502f0 · outbound
This paper cites L., McDougall, C., MacDiarmid, M., Freeman, C.
Sparse Autoencoders Trained on the Same Data Learn Different Features L., McDougall, C., MacDiarmid, M., Freeman, C
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T11:58:37.331025Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 5a507f8f-967b-44f5-bff3-5a3cd4c269fa · inbound
Disentangling Polysemantic Channels in Convolutional Neural Networks cites this paper.
Disentangling Polysemantic Channels in Convolutional Neural Networks Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T12:29:34.117929Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a09a1d52-0f7d-41f8-b339-771d5f45fd76 · inbound
On the Mechanistic Interpretability of Neural Networks for Causality in Bio-statistics cites this paper.
On the Mechanistic Interpretability of Neural Networks for Causality in Bio-statistics Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:43:33.510286Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0174c757-c952-4a4b-86e9-ca37bda1d101 · inbound
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs cites this paper.
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T14:03:02.656998Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06b9e522-c648-4149-9ad9-84b9f48bbed5 · inbound
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies cites this paper.
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:06.700396Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dc209aea-5f78-4784-8b2b-721e8c69e9c1 · inbound
Cross-Layer Discrete Concept Discovery for Interpreting Language Models cites this paper.
Cross-Layer Discrete Concept Discovery for Interpreting Language Models Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:03:05.002183Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff41e61b-766f-4041-a24f-b844fb5c9680 · inbound
Prompting as Scientific Inquiry cites this paper.
Prompting as Scientific Inquiry Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T21:25:08.563819Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 737c8818-a4d5-49f2-adf8-d23dba927c0c · inbound
On the transferability of Sparse Autoencoders for interpreting compressed models cites this paper.
On the transferability of Sparse Autoencoders for interpreting compressed models Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T15:24:45.771905Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 96cfe9ce-a37d-41f3-9def-752e842cb6ed · inbound
Distribution-Aware Feature Selection for SAEs cites this paper.
Distribution-Aware Feature Selection for SAEs Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:27:25.446156Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 604047c3-fb81-49ed-a662-0554daae9874 · inbound
Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal cites this paper.
Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T18:56:45.869896Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 87e2e879-2d3f-405e-bc86-af6306f63ba6 · inbound
Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders cites this paper.
Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T15:47:51.634104Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ef256f4-6bf1-4861-8920-fb80ba4b947c · inbound
Graph-Regularized Sparse Autoencoders for LLM Safety Steering cites this paper.
Graph-Regularized Sparse Autoencoders for LLM Safety Steering Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T18:40:28.874914Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 3c5d7cb2-6517-445b-ae97-d837dff27bbc · inbound
Stable and Steerable Sparse Autoencoders with Weight Regularization cites this paper.
Stable and Steerable Sparse Autoencoders with Weight Regularization Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T18:56:19.219712Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6253079f-de55-414a-8388-6abd2c21f1dd · inbound
Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction cites this paper.
Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T11:11:06.192503Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 8f529f43-7303-4ee8-b6f7-cda07b545ca3 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.
WriteSAE: Sparse Autoencoders for Recurrent State Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 33
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-21T07:49:50.201457Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 5e5456da-86ce-4424-ac82-6214d1e99445 · inbound
Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features cites this paper.
Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T20:29:27.952393Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 870c7a5c-33b1-4e92-b8ed-6c240305a6e8 · inbound
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy cites this paper.
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 26
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-14T20:07:53.668806Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 920ff42f-aa84-4540-9e20-dbc511288f18 · inbound
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy cites this paper.
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 26
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T21:33:46.448245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c10ecae9-98b8-4af9-996a-8b372b587cfa · inbound
Exemplar Partitioning for Mechanistic Interpretability cites this paper.
Exemplar Partitioning for Mechanistic Interpretability Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 39
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T01:38:27.619659Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation e017d5f4-b1cf-44c1-9126-5ecb13237715 · inbound
Exemplar Partitioning for Mechanistic Interpretability cites this paper.
Exemplar Partitioning for Mechanistic Interpretability Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 39
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T20:53:43.657427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 3623622e-bbb4-4e41-9730-bde521d597c8 · inbound
Are Sparse Autoencoder Benchmarks Reliable? cites this paper.
Are Sparse Autoencoder Benchmarks Reliable? Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 26
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T12:43:16.769836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 7a86f942-362b-4781-9267-52c324587e07 · inbound
Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.
Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-29T14:23:30.747731Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 7a1642d3-caee-46c9-b097-d03ebf4a24e4 · inbound
Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.
Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T05:02:51.333339Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c0265fb-1f6a-4a1a-9e76-8882165393e5 · inbound
Perplexity Can Miss SAE Feature Damage Under Quantization cites this paper.
Perplexity Can Miss SAE Feature Damage Under Quantization Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T01:36:25.811675Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation aa9ccb36-7ef4-4339-aec7-4877f0238e81 · inbound
Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders cites this paper.
Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-06-27T10:40:49.834013Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 6a79cf32-e615-43a7-ba6a-a42e6b690332 · inbound
At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization cites this paper.
At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-06-26T01:28:50.521664Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 7f3991a4-2cfc-4c71-ba73-4a9b1db256e0 · inbound
Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources cites this paper.
Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T03:00:02.282468Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 196abc9d-4b93-424c-a922-f9d8a4d1c5cc · inbound
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects cites this paper.
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T10:03:58.308413Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cbe84711-72a2-4c18-be10-956fcee445b3 · inbound
From Found to Designed: Concepts as a Design Axis for Large Language Models cites this paper.
From Found to Designed: Concepts as a Design Axis for Large Language Models Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-07-30T19:59:23.290640Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8a26eaee-def6-4030-a281-a4d2db4d5cb9 · inbound
From Found to Designed: Concepts as a Design Axis for Large Language Models cites this paper.
From Found to Designed: Concepts as a Design Axis for Large Language Models Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T10:48:50.463361Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fb5c0c8f-57be-4e01-8c52-d49b6e36df09 · inbound
Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation cites this paper.
Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation Sparse Autoencoders Trained on the Same Data Learn Different Features
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-14T13:29:00.224169Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.