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. 12038
    Prev
    Next
    INDEX
    Explanations

    Math formulas

    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
     ///
    -0.08
     cwd
    -0.08
    _NOW
    -0.08
     писать
    -0.07
    đer
    -0.07
     वर्षीय
    -0.07
    注意
    -0.07
    iferay
    -0.07
     proteger
    -0.07
     tawm
    -0.07
    POSITIVE LOGITS
    termin
    0.08
    {↵↵
    0.07
     essence
    0.07
    decimal
    0.07
     Na
    0.07
    ορ
    0.07
    {
    ↵
    ↵
    0.07
    display
    0.07
     decre
    0.07
    desired
    0.07
    Activations Density 0.197%

    No Known Activations