© 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. 81
    Prev
    Next
    INDEX
    Explanations

    food

    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
     pav
    -0.08
     INVENT
    -0.08
     HAC
    -0.08
    merkt
    -0.07
     acteurs
    -0.07
    ظر
    -0.07
     अभिन
    -0.07
     mj
    -0.07
     TOO
    -0.07
     mengatakan
    -0.07
    POSITIVE LOGITS
     uống
    0.09
     liệu
    0.08
    ಿಕೆಯ
    0.08
     beating
    0.08
     bagi
    0.08
     impulses
    0.08
     feeding
    0.08
    ಕ್ಕಾಗಿ
    0.08
     bath
    0.08
     공급
    0.07
    Activations Density 0.031%

    No Known Activations