Paper Citation Record · LEDGER

Transcoders Beat Sparse Autoencoders for Interpretability

As of 22 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 15 inbound Pith citation observations for arXiv:2501.18823.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2501.18823 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T22:24:53.899236Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:51:54.930894Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T00:07:28.632106Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy13
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ff980a68-7ac6-4f52-b33f-861499eda96b · outbound

This paper cites write newline.

Transcoders Beat Sparse Autoencoders for Interpretability write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.779467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22ef0f91-5384-4edd-ae4b-0689fe697a6a · outbound

This paper cites write newline.

Transcoders Beat Sparse Autoencoders for Interpretability write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.783908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1deecc2a-75a9-4a21-8d97-7fc1af5964f5 · outbound

This paper cites Linear algebraic structure of word senses, with applications to polysemy.

Transcoders Beat Sparse Autoencoders for Interpretability Linear algebraic structure of word senses, with applications to polysemy

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.787898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f75f0885-0c9d-4757-85d2-b0dd53aa682d · outbound

This paper cites Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs.

Transcoders Beat Sparse Autoencoders for Interpretability Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.791376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ceac99-7411-4570-8fd5-1c8e73cd3969 · outbound

This paper cites Mechanistic Permutability: Match Features Across Layers.

Transcoders Beat Sparse Autoencoders for Interpretability Mechanistic Permutability: Match Features Across Layers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.794990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c92d59d-ecd3-48c4-bba3-55e9d361e7ac · outbound

This paper cites and Baraniuk, R.

Transcoders Beat Sparse Autoencoders for Interpretability and Baraniuk, R

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.323697Z

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 171141ac-5dd8-443d-9911-fbc3b5c474a8 · outbound

This paper cites G., Bradley, H., O’Brien, K., Hallahan, E., Khan, M.

Transcoders Beat Sparse Autoencoders for Interpretability G., Bradley, H., O’Brien, K., Hallahan, E., Khan, M

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.801561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 183bc9a1-993c-46aa-a87f-aec5fa3beb1d · outbound

This paper cites Language models can explain neurons in language models.

Transcoders Beat Sparse Autoencoders for Interpretability Language models can explain neurons in language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.307594Z

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 34ecd6ab-fc1a-4ff6-9fd1-d4953946937e · outbound

This paper cites Interpreting Neural Networks through the Polytope Lens.

Transcoders Beat Sparse Autoencoders for Interpretability Interpreting Neural Networks through the Polytope Lens

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.807886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2286ff-1297-4bc4-b0e3-70a2126e340c · outbound

This paper cites E., Hume, T., Carter, S., Henighan, T., and Olah, C.

Transcoders Beat Sparse Autoencoders for Interpretability E., Hume, T., Carter, S., Henighan, T., and Olah, C

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.297725Z

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 5a83ef4a-c769-4058-bbf5-cf57a4232c51 · 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.

Transcoders Beat Sparse Autoencoders for Interpretability 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 2026-08-09T22:24:54.287944Z

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 c0e40d2d-ca77-4bc1-be06-adb47144d086 · outbound

This paper cites Learning multi-level features with matryoshka saes.

Transcoders Beat Sparse Autoencoders for Interpretability Learning multi-level features with matryoshka saes

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.278822Z

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 32562f45-8c26-4456-af7b-cfbeb6f2ac8f · outbound

This paper cites BatchTopK Sparse Autoencoders.

Transcoders Beat Sparse Autoencoders for Interpretability BatchTopK Sparse Autoencoders

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.819540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 389ab1e5-e18c-4de9-867d-e47d9a8d8a5a · outbound

This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoencoders.

Transcoders Beat Sparse Autoencoders for Interpretability A is for absorption: Studying feature splitting and absorption in sparse autoencoders

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.822566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8eeb20a-a837-4c55-896a-7ecb026afc01 · outbound

This paper cites Redpajama: an open dataset for training large language models, 2023.

Transcoders Beat Sparse Autoencoders for Interpretability Redpajama: an open dataset for training large language models, 2023

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.268578Z

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 69061fed-e49d-4c2b-8b98-dd09645abde2 · outbound

This paper cites Towards Automated Circuit Discovery for Mechanistic Interpretability.

Transcoders Beat Sparse Autoencoders for Interpretability Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.827765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395cc7e1-7f8b-4705-9253-755d0aa90007 · outbound

This paper cites The Llama 3 Herd of Models.

Transcoders Beat Sparse Autoencoders for Interpretability The Llama 3 Herd of Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.830800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e814619-2107-4595-9062-a38af8b9a3cd · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Transcoders Beat Sparse Autoencoders for Interpretability Transcoders Find Interpretable LLM Feature Circuits

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.833482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df94c201-6434-452c-b0bd-d3f2697fb5e2 · outbound

This paper cites Toy Models of Superposition.

Transcoders Beat Sparse Autoencoders for Interpretability Toy Models of Superposition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.836288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1633fff6-25b8-475b-910f-d95bf28d11e6 · outbound

This paper cites Decomposing The Dark Matter of Sparse Autoencoders.

Transcoders Beat Sparse Autoencoders for Interpretability Decomposing The Dark Matter of Sparse Autoencoders

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.839060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ecd7d15-425d-4c92-8168-8b4d661dbcc7 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Transcoders Beat Sparse Autoencoders for Interpretability The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.841938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92cfc6f-07db-40e1-af73-6b5443be6c4d · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Transcoders Beat Sparse Autoencoders for Interpretability Scaling and evaluating sparse autoencoders

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.844765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbe171f0-b4e3-422f-9576-ec5e485081a1 · outbound

This paper cites Openwebtext corpus.

Transcoders Beat Sparse Autoencoders for Interpretability Openwebtext corpus

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.847517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a12753-7b4d-4ee9-b5d2-14881b336d8d · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Transcoders Beat Sparse Autoencoders for Interpretability DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.850177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ebfe189-4b58-4945-9c96-e72c608cf0cc · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Transcoders Beat Sparse Autoencoders for Interpretability Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.852861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b284469-f521-48a7-8ea5-57e1dedfdef2 · outbound

This paper cites Universal Neurons in GPT2 Language Models.

Transcoders Beat Sparse Autoencoders for Interpretability Universal Neurons in GPT2 Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.855675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 818139f1-5ca3-4a22-a4e3-edec26335ba1 · outbound

This paper cites and Templeton, A.

Transcoders Beat Sparse Autoencoders for Interpretability and Templeton, A

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.252911Z

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 0ce159be-dc41-4fcf-896d-9e2740c0b022 · outbound

This paper cites Open source automated interpretability for sparse autoencoder features, July 2024.

Transcoders Beat Sparse Autoencoders for Interpretability Open source automated interpretability for sparse autoencoder features, July 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.243477Z

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 d99addce-95f8-44be-894f-8742ecf48bff · outbound

This paper cites Saebench: A comprehensive benchmark for sparse autoencoders, 2024.

Transcoders Beat Sparse Autoencoders for Interpretability Saebench: A comprehensive benchmark for sparse autoencoders, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.233599Z

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 5b7092ab-42a5-4337-b731-bfb30cf0c284 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Transcoders Beat Sparse Autoencoders for Interpretability Adam: A Method for Stochastic Optimization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.867368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 837accc0-d372-44ad-95a2-468329773b9b · outbound

This paper cites dictionary\_learning repository, 2023.

Transcoders Beat Sparse Autoencoders for Interpretability dictionary\_learning repository, 2023

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.222989Z

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 641a3294-e646-4bd9-8b15-5d1d54510444 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Transcoders Beat Sparse Autoencoders for Interpretability Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.872872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3aeeeab-a92a-4579-8e2e-1c08ed9acdea · outbound

This paper cites and Black, S.

Transcoders Beat Sparse Autoencoders for Interpretability and Black, S

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.876083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebddf325-94da-4cc4-b676-e1c83342243a · outbound

This paper cites Matryoshka sparse autoencoders.

Transcoders Beat Sparse Autoencoders for Interpretability Matryoshka sparse autoencoders

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.207509Z

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 c73c176d-a85c-43b6-aed6-04752cfb4e1c · outbound

This paper cites Zoom in: An introduction to circuits.

Transcoders Beat Sparse Autoencoders for Interpretability Zoom in: An introduction to circuits

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.881587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3227a6-362c-4f27-9081-ab790f79be4d · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Transcoders Beat Sparse Autoencoders for Interpretability Automatically Interpreting Millions of Features in Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.884852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5345284-d47d-47ee-8b94-e6238ff5ea68 · outbound

This paper cites B., Lozhkov, A., Mitchell, M., Raffel, C., Werra, L.

Transcoders Beat Sparse Autoencoders for Interpretability B., Lozhkov, A., Mitchell, M., Raffel, C., Werra, L

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.887575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68e6aca4-03a4-4a3a-89ba-c2b5f79cbd5b · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Transcoders Beat Sparse Autoencoders for Interpretability Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.890411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae0c6696-fcc1-4806-8547-36b3c200c9f0 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Transcoders Beat Sparse Autoencoders for Interpretability Gemma 2: Improving Open Language Models at a Practical Size

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.893458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2122e0c-0eea-4d37-860a-88768c3e5d5c · outbound

This paper cites Predicting future activations.

Transcoders Beat Sparse Autoencoders for Interpretability Predicting future activations

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.191982Z

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 d504b34f-91c6-413d-a3b8-897d9553d8ef · outbound

This paper cites L., McDougall, C., MacDiarmid, M., Freeman, C.

Transcoders Beat Sparse Autoencoders for Interpretability L., McDougall, C., MacDiarmid, M., Freeman, C

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:24:54.182000Z

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.

Pith citing papers

Observation d946496c-4574-4620-ba8c-415dd49173f8 · inbound

Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data cites this paper.

Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data Transcoders Beat Sparse Autoencoders for Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T19:51:54.930894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2d350c-cb39-4c0f-a65c-3cbc13eb9773 · inbound

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation cites this paper.

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation Transcoders Beat Sparse Autoencoders for Interpretability

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T18:47:45.267469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc1aede-4cea-4018-8c24-e849deda137a · inbound

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach cites this paper.

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach Transcoders Beat Sparse Autoencoders for Interpretability

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:00:40.064145Z

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 c7f318a9-708d-40f5-bdcf-ec8586895f68 · inbound

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach cites this paper.

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach Transcoders Beat Sparse Autoencoders for Interpretability

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T00:23:29.105938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb10d04b-b467-4a0c-9798-ec2865a3e301 · inbound

Improving Robustness In Sparse Autoencoders via Masked Regularization cites this paper.

Improving Robustness In Sparse Autoencoders via Masked Regularization Transcoders Beat Sparse Autoencoders for Interpretability

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:55:51.706772Z

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 3d5a7cdd-308c-4eb7-aceb-ab156224698d · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Transcoders Beat Sparse Autoencoders for Interpretability

Reference 82

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:59:28.558798Z

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 e9270133-f940-483f-bae7-05cf498133f4 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Transcoders Beat Sparse Autoencoders for Interpretability

Reference 82

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T04:59:45.253775Z

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 3141c122-7565-4733-93fa-82bf691bff82 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Transcoders Beat Sparse Autoencoders for Interpretability

Reference 82

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T21:53:47.213529Z

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 ee2ed23b-0ccf-442a-8ca6-883847cd3c92 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Transcoders Beat Sparse Autoencoders for Interpretability

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:50.090433Z

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 9c655d3f-e870-4ddb-81b2-5819a0ea2fad · inbound

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift cites this paper.

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Transcoders Beat Sparse Autoencoders for Interpretability

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:16:16.144308Z

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 12c2ecd1-63ed-4ae3-a766-263a3282c8b5 · inbound

Interactions Between Crosscoder Features: A Compact Proofs Perspective cites this paper.

Interactions Between Crosscoder Features: A Compact Proofs Perspective Transcoders Beat Sparse Autoencoders for Interpretability

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:07:28.633788Z

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 1f9592c2-90e0-4c90-8058-7b157fe71aae · inbound

Transcoders for Investigating Deception in Language Models cites this paper.

Transcoders for Investigating Deception in Language Models Transcoders Beat Sparse Autoencoders for Interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T01:06:13.642977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c532033-01e8-40d0-9379-caa8dc15910d · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Transcoders Beat Sparse Autoencoders for Interpretability

Reference 140

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:30.763794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 543bdd20-a41a-4afd-a618-ce2f082335bd · inbound

Evading Chain-of-Thought Monitoring Through Model Poisoning cites this paper.

Evading Chain-of-Thought Monitoring Through Model Poisoning Transcoders Beat Sparse Autoencoders for Interpretability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.266417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39137c1-d6e6-4e27-838f-4d3f4bb6b6ac · inbound

Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability cites this paper.

Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability Transcoders Beat Sparse Autoencoders for Interpretability

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T04:21:09.505809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.