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. 58857
    Prev
    Next
    INDEX
    Explanations

    suffix "ary" or "io"

    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
     盐
    -0.08
     ek
    -0.08
     drast
    -0.07
     helper
    -0.07
    扑
    -0.07
     matching
    -0.07
    ?”
    -0.07
     szám
    -0.07
     dialog
    -0.07
     vastly
    -0.07
    POSITIVE LOGITS
     Bann
    0.08
     продукт
    0.08
     bleed
    0.08
     Wishes
    0.08
     Loves
    0.08
     Stand
    0.08
     uterus
    0.07
    stand
    0.07
     Queens
    0.07
     thinks
    0.07
    Activations Density 0.001%

    No Known Activations