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. 58540
    Prev
    Next
    INDEX
    Explanations

    oct

    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
    :path
    -0.08
     certa
    -0.08
     Karin
    -0.08
    -0.08
    ßt
    -0.08
     kleines
    -0.08
     Juven
    -0.07
     kurzer
    -0.07
     صغيرة
    -0.07
     Rana
    -0.07
    POSITIVE LOGITS
     Advantage
    0.09
    adecimal
    0.08
     fugit
    0.08
     Really
    0.07
    operator
    0.07
     echiche
    0.07
     instinct
    0.07
    stim
    0.07
    olar
    0.07
     超
    0.07
    Activations Density 0.005%

    No Known Activations