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. 58750
    Prev
    Next
    INDEX
    Explanations

    unit conversions

    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
     Puff
    -0.08
     premises
    -0.08
    armor
    -0.08
    ska
    -0.08
     Gustavo
    -0.08
    yay
    -0.08
    �
    -0.07
     guna
    -0.07
     புத்த
    -0.07
     fetal
    -0.07
    POSITIVE LOGITS
    Daniel
    0.07
    Institute
    0.07
    ප
    0.07
    Dog
    0.07
     powder
    0.07
    0.07
     हाल
    0.07
     dog
    0.07
    إ
    0.07
     Cox
    0.07
    Activations Density 0.010%

    No Known Activations