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. 112093
    Prev
    Next
    INDEX
    Explanations

    long

    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
    isee
    -0.09
     подробнее
    -0.09
    ubr
    -0.08
     preorder
    -0.08
     Pep
    -0.07
    agize
    -0.07
     gives
    -0.07
    amer
    -0.07
     Clarke
    -0.07
     prere
    -0.07
    POSITIVE LOGITS
     décadas
    0.09
     conceptual
    0.09
     delayed
    0.08
     decades
    0.08
     tarda
    0.08
     lenta
    0.08
     धी
    0.08
     mobili
    0.08
     retard
    0.07
     akty
    0.07
    Activations Density 0.029%

    No Known Activations