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. 12228
    Prev
    Next
    INDEX
    Explanations

    distance

    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
     konkrete
    -0.08
     комбина
    -0.08
    _needed
    -0.08
    TOCOL
    -0.08
    ্ত
    -0.07
     шт
    -0.07
     adapting
    -0.07
    Needed
    -0.07
     конструк
    -0.07
     упражнения
    -0.07
    POSITIVE LOGITS
     Mene
    0.08
    epers
    0.08
    ístup
    0.08
     waarop
    0.08
     dormir
    0.07
     Hulk
    0.07
     kidding
    0.07
    /google
    0.07
     soleil
    0.07
     forehead
    0.07
    Activations Density 0.013%

    No Known Activations