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. 58539
    Prev
    Next
    INDEX
    Explanations

    description

    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
     rağmen
    -0.08
     miserable
    -0.08
     copie
    -0.07
     runoff
    -0.07
    _POOL
    -0.07
     morali
    -0.07
    pargne
    -0.07
    _SET
    -0.07
     quotas
    -0.07
    _SMS
    -0.07
    POSITIVE LOGITS
     inventions
    0.09
     Exotic
    0.09
    stick
    0.08
     stick
    0.08
     inom
    0.08
     exot
    0.08
     Stick
    0.08
     exotic
    0.08
    нік
    0.08
     nouns
    0.08
    Activations Density 0.003%

    No Known Activations