Paper Citation Record · LEDGER

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

As of 7 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 3 inbound Pith citation observations for arXiv:2505.24473.

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

pith.paper-citation-record.v1
2505.24473 v2

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:35:26.516648Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T13:34:46.646854Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T20:38:55.913976Z

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy0
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 730178f5-97aa-41a0-b29d-50ce90e816e5 · outbound

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

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:24.960957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce60702-03f3-4600-bada-1ab56a1179f5 · outbound

This paper cites an unresolved cited work.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.128210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 853c427a-e857-45d2-8e00-188440d1c678 · outbound

This paper cites BatchTopK Sparse Autoencoders.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy BatchTopK Sparse Autoencoders

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.286393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50c042c0-98a9-45b1-80ca-1b9e07b552cf · outbound

This paper cites Learning Multi-Level Features with Matryoshka Sparse Autoencoders.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.410836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8543effd-c990-4799-9abb-1d90c4848b2d · outbound

This paper cites an unresolved cited work.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:27.439501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bdbdfb25-b61a-4b30-99dc-88e58d30767c · outbound

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

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Gemma 2: Improving Open Language Models at a Practical Size

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.692547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a4d355-2fc2-4888-a10d-f5e945759d3e · outbound

This paper cites SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.837701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ee83a63-ecbf-4803-8824-667a3e74b5be · outbound

This paper cites an unresolved cited work.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:27.245041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2ee52649-4fbc-48d9-bb86-fef641b1ab21 · outbound

This paper cites an unresolved cited work.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:27.036818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0dced67a-930b-4899-906d-9d518eb3e32c · outbound

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

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Automatically Interpreting Millions of Features in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.125107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d77a32b3-1d89-4d15-ba85-b29305c513e0 · outbound

This paper cites an unresolved cited work.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:26.880763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 46932a4e-44c9-491b-9221-7b4410c8e8a2 · outbound

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

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.310145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf71130b-b396-401c-b794-3a020db5d2dd · outbound

This paper cites online" 'onlinestring :=.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy online" 'onlinestring :=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.415785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d3e4c7b-b17c-429f-97d9-a178852a3527 · outbound

This paper cites write newline.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy write newline

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.516648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 420241b2-e291-4a1f-87a2-3b09172c2295 · inbound

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds cites this paper.

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:16:19.130191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6c712783-36d0-437b-827c-62db3bff6981 · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

Reference 89

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:38:55.915570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 406ac0ee-6bc1-4c11-bf01-a4c08aaf6fef · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T13:34:46.646854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.