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. 53097
    Prev
    Next
    INDEX
    Explanations

    type

    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
     Decor
    -0.08
     Diocese
    -0.08
    ്റെ
    -0.08
     Martínez
    -0.08
    (groups
    -0.07
    ава
    -0.07
     disturbed
    -0.07
     exh
    -0.07
     Marche
    -0.07
     wiederum
    -0.07
    POSITIVE LOGITS
     ulang
    0.09
     aloud
    0.08
    writer
    0.08
    grow
    0.08
    些什么
    0.08
    Ahead
    0.07
    Ln
    0.07
    etik
    0.07
     FED
    0.07
    felt
    0.07
    Activations Density 0.014%

    No Known Activations