Scholar
Narmeen Oozeer
Google Scholar ID: PtYiVrQAAAAJ
Research Engineer, Martian Learning
mathematics
deep learning
interpretability
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
4
H-index
1
i10-index
0
Publications
9
Co-authors
0
Contact
No contact links provided.
Publications
9 items
Understanding and Mitigating Dataset Corruption in LLM Steering
2026
Cited
0
Spectral Superposition: A Theory of Feature Geometry
2026
Cited
0
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
2026
Cited
0
Position: Require Frontier AI Labs To Release Small "Analog" Models
2025
Cited
0
Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
2025
Cited
0
Distribution-Aware Feature Selection for SAEs
2025
Cited
0
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
2025
Cited
0
Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Large Language Models
2025
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up