Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75250
    Prev
    Next
    INDEX
    Explanations

    BIOS, OS

    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
     Dang
    -0.08
     deducted
    -0.08
     recreational
    -0.08
     American
    -0.07
     prairie
    -0.07
    वाही
    -0.07
     oasis
    -0.07
     Basin
    -0.07
     Andrea
    -0.07
    西
    -0.07
    POSITIVE LOGITS
     BIOS
    0.09
    품
    0.09
     часы
    0.08
    (SDL
    0.08
     طف
    0.08
     hodin
    0.08
     결정
    0.08
    _ROM
    0.08
    /CD
    0.08
     HID
    0.08
    Activations Density 0.002%

    No Known Activations