Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53202
    Prev
    Next
    INDEX
    Explanations

    gingko

    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
     ಮನೆ
    -0.09
    :red
    -0.08
     Jou
    -0.08
     Red
    -0.08
    ಕ
    -0.08
     घर
    -0.08
     Bour
    -0.08
    (red
    -0.08
     encont
    -0.08
     Mus
    -0.08
    POSITIVE LOGITS
     đôi
    0.08
     walnuts
    0.08
     alas
    0.08
     eagle
    0.07
    _png
    0.07
    迟
    0.07
     lamin
    0.07
    一卡
    0.07
     Nish
    0.07
     Alzheimer's
    0.07
    Activations Density 0.001%

    No Known Activations