Scholar

Stefan Heimersheim

Google Scholar ID: PX37V5AAAAAJ

Apollo Research

Google Scholar↗

Citations & Impact

All-time

Citations

1,124

H-index

12

i10-index

13

Publications

20

Co-authors

4

list available

Contact

No contact links provided.

Publications

13 items

Compressed Computation under $L^4$ Loss is likely Computation in Superposition

2026

Cited

0

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

2026

Cited

0

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

2026

Cited

0

Evidence for feature-specific error correction in LLMs

2026

Cited

0

Compressed Computation is (probably) not Computation in Superposition

2026

Cited

0

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes

2026

Cited

0

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

2026

Cited

0

SCALAR: Benchmarking SAE Interaction Sparsity in Toy LLMs

2025

Cited

0

Resume (English only)

Co-authors

4 total

University College London

Adrià Garriga-Alonso

Research Scientist, FAR AI