Scholar
Michael Lan
Google Scholar ID: 6cDvEdkAAAAJ
Martian
AI safety
AI interpretability
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
83
H-index
5
i10-index
2
Publications
18
Co-authors
0
Publications
4 items
Reasoning Fine-Tuning Induces Persistent Latent Policy States
2026
Cited
0
Distribution-Aware Feature Selection for SAEs
2025
Cited
0
Activation Space Interventions Can Be Transferred Between Large Language Models
2025
Cited
0
Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
arXiv.org · 2024
Cited
4
