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. 58864
    Prev
    Next
    INDEX
    Explanations

    Brené Brown

    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
    .SQLite
    -0.09
     Interpret
    -0.08
     GLenum
    -0.08
     statutes
    -0.08
     backing
    -0.08
     Texte
    -0.08
    _Ph
    -0.08
     statute
    -0.08
     SQLite
    -0.08
    .GREEN
    -0.08
    POSITIVE LOGITS
    羞
    0.09
     courageous
    0.09
     wholehearted
    0.08
    Erro
    0.08
    վող
    0.08
     Hui
    0.08
     panan
    0.08
    _fu
    0.08
    overflow
    0.08
    成为
    0.08
    Activations Density 0.003%

    No Known Activations