© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47141
    Prev
    Next
    INDEX
    Explanations

    legal claims and patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ится
    -0.09
    ]+"
    -0.09
     Kama
    -0.09
     Pokémon
    -0.09
    uffman
    -0.08
     сотрудники
    -0.08
    )!↵↵
    -0.08
     HAM
    -0.08
     температура
    -0.08
     وروسته
    -0.08
    POSITIVE LOGITS
     breadth
    0.08
    capture
    0.08
    docker
    0.08
     clauses
    0.08
     claus
    0.07
     joints
    0.07
     tissu
    0.07
     boldly
    0.07
     cláus
    0.07
     docker
    0.07
    Activations Density 0.006%

    No Known Activations