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. 65293
    Prev
    Next
    INDEX
    Explanations

    Regions/French locations

    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
    <ID
    -0.08
     OSHA
    -0.08
    itness
    -0.07
     whenever
    -0.07
    ('+
    -0.07
     oatmeal
    -0.07
     Testosterone
    -0.07
     skyrock
    -0.07
    .hm
    -0.07
     milestone
    -0.07
    POSITIVE LOGITS
    自治区
    0.12
     province
    0.11
     provinces
    0.11
     Province
    0.11
     प्रदेश
    0.10
    Province
    0.10
     departments
    0.09
    province
    0.09
     southern
    0.09
     ಇಲಾಖೆ
    0.09
    Activations Density 0.031%

    No Known Activations