© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    fear

    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
    085
    -0.09
     Wann
    -0.08
    邦
    -0.07
    .uint
    -0.07
     Mahar
    -0.07
    府
    -0.07
     Fuk
    -0.07
     Bennett
    -0.07
    Peek
    -0.07
     Kee
    -0.07
    POSITIVE LOGITS
    fully
    0.09
    fulness
    0.09
    倒
    0.08
    lessness
    0.08
    /conf
    0.07
    panic
    0.07
    -provoking
    0.07
    finding
    0.07
    Todos
    0.07
    抱
    0.07
    Activations Density 0.015%

    No Known Activations