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. 43809
    Prev
    Next
    INDEX
    Explanations

    mixed languages

    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
     Annual
    -0.08
    Annual
    -0.08
     annually
    -0.08
    。截至
    -0.08
     annuelle
    -0.08
    中心
    -0.07
     jaarlijkse
    -0.07
     champion
    -0.07
    年度
    -0.07
    Nous
    -0.07
    POSITIVE LOGITS
     calmly
    0.10
     早餐
    0.10
     soothing
    0.10
     breakfast
    0.10
     creamy
    0.10
     desayuno
    0.09
     খাব
    0.09
     السكر
    0.09
     soothe
    0.09
     peppermint
    0.09
    Activations Density 0.011%

    No Known Activations