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. 78698
    Prev
    Next
    INDEX
    Explanations

    Style descriptions

    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
     prej
    -0.09
     coinc
    -0.09
    届
    -0.08
     உள்ளிட்ட
    -0.08
     ;↵//
    -0.08
     nro
    -0.08
     необходимо
    -0.08
     علا
    -0.08
     彩票
    -0.07
     عمل
    -0.07
    POSITIVE LOGITS
     UC
    0.09
     Asp
    0.08
    Gee
    0.07
    Asp
    0.07
    /**/*
    0.07
    vt
    0.07
     Versch
    0.07
     cheerful
    0.07
     delight
    0.07
     wide
    0.07
    Activations Density 0.006%

    No Known Activations