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. 30596
    Prev
    Next
    INDEX
    Explanations

    arithmetic calculations

    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
     contraintes
    -0.08
     nằm
    -0.08
    essential
    -0.07
    zing
    -0.07
    сы
    -0.07
    peza
    -0.07
     praticamente
    -0.07
     Cycling
    -0.07
    imb
    -0.07
     Rhodes
    -0.07
    POSITIVE LOGITS
    merking
    0.08
     assuming
    0.08
    nię
    0.07
    Poss
    0.07
     komin
    0.07
    assuming
    0.07
    That's
    0.07
     dune
    0.07
     السب
    0.07
    Oops
    0.07
    Activations Density 0.104%

    No Known Activations