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. 53841
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     feather
    -0.08
    ультура
    -0.08
     ((!
    -0.08
     планш
    -0.08
     beck
    -0.07
     komo
    -0.07
    -fed
    -0.07
     aggression
    -0.07
    activation
    -0.07
    leet
    -0.07
    POSITIVE LOGITS
    ,因此
    0.10
    ,在
    0.08
    ,这是
    0.08
    Bins
    0.08
    ,这
    0.08
    ,与
    0.08
     that's
    0.08
     nhiên
    0.08
     we'll
    0.08
    ,通过
    0.08
    Activations Density 0.038%

    No Known Activations