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. 30730
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
     exchanges
    -0.08
     Exchanges
    -0.08
    exchange
    -0.08
     negotiating
    -0.08
     substr
    -0.08
     exchange
    -0.08
     échanges
    -0.08
    excluding
    -0.07
     residues
    -0.07
     ends
    -0.07
    POSITIVE LOGITS
     ভোট
    0.08
     מקום
    0.08
     bols
    0.08
     स्लॉट
    0.08
     chairs
    0.07
     muffin
    0.07
    杯
    0.07
     ভার
    0.07
     claw
    0.07
     каждому
    0.07
    Activations Density 0.015%

    No Known Activations