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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12171
    Prev
    Next
    INDEX
    Explanations

    wine sweetness

    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
     grou
    -0.08
     yards
    -0.08
     cabel
    -0.08
    偷
    -0.08
     optimization
    -0.08
    onacci
    -0.08
     rooft
    -0.08
     memorize
    -0.08
     Intel
    -0.08
     squirrels
    -0.08
    POSITIVE LOGITS
    /dialog
    0.08
    Variant
    0.08
     nominal
    0.08
     ต่ำ
    0.08
     relig
    0.08
     наполн
    0.07
     lactose
    0.07
    /sh
    0.07
    _variant
    0.07
     hybrids
    0.07
    Activations Density 0.010%

    No Known Activations