Paper Citation Record · LEDGER

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders

As of 22 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2509.22015.

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

pith.paper-citation-record.v1
2509.22015 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:47:51.645258Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eaa22dd1-d7a6-4843-b45c-ed10aaaad849 · outbound

This paper cites GPT-4 Technical Report.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.593428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbdebc2c-9558-403e-9072-9bfad8a3ed4b · outbound

This paper cites Measuring and guiding monosemanticity.arXiv preprint arXiv:2506.19382,.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Measuring and guiding monosemanticity.arXiv preprint arXiv:2506.19382,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.611878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4ce5d3e-ff1d-4963-8ea3-ea8999e7403f · outbound

This paper cites Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.622241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530263d6-1560-485d-8a2f-8fb22163af40 · outbound

This paper cites Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.629363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e2e879-2d3f-405e-bc86-af6306f63ba6 · outbound

This paper cites Sparse Autoencoders Trained on the Same Data Learn Different Features.

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 c8dd53a9-130f-4a2e-b0ac-b66287613b26 · outbound

This paper cites Sparse autoencoders for scientifi- cally rigorous interpretation of vision models.arXiv preprint arXiv:2502.06755,.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Sparse autoencoders for scientifi- cally rigorous interpretation of vision models.arXiv preprint arXiv:2502.06755,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.645258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75dcd44b-3237-4cac-adaa-35f999a0c587 · outbound

This paper cites Probing the representational power of sparse autoencoders in vision models.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Probing the representational power of sparse autoencoders in vision models

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.625679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43672443-5ff1-4ca9-958f-ea43dedd0fba · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.597793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43afc60e-3db0-48f9-baca-81ef6fb476eb · outbound

This paper cites The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.608417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f21efe39-39bb-4144-a3b2-504a395b8798 · outbound

This paper cites Sparse autoencoders reveal selective remapping of visual concepts during adaptation.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Sparse autoencoders reveal selective remapping of visual concepts during adaptation

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.618582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da5f995-56b7-4f13-995a-a06f4e0a9486 · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.637813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f984870d-f914-497a-a973-1afdab20fb72 · outbound

This paper cites A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.641266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a2722ee-d0f6-4f58-a951-615b68c6f11c · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Scaling and evaluating sparse autoencoders

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.600961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f747386e-7d44-4d4d-b5f1-5f44144845c4 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Explaining and Harnessing Adversarial Examples

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.605107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78693a05-f1b1-45c4-b6e3-e9124995f074 · outbound

This paper cites Interpreting Attention Layer Outputs with Sparse Autoencoders.

Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders Interpreting Attention Layer Outputs with Sparse Autoencoders

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:51.614985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.