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. 120313
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     elimin
    -0.09
    Defs
    -0.08
     débarr
    -0.08
    downloads
    -0.08
     priest
    -0.08
    .Err
    -0.08
    defs
    -0.07
    esten
    -0.07
     searches
    -0.07
    cel
    -0.07
    POSITIVE LOGITS
     Jensen
    0.10
     convex
    0.09
     Blend
    0.09
     averaging
    0.09
    Blend
    0.09
    weighted
    0.09
     homogen
    0.09
     آموزشی
    0.09
     Weighted
    0.08
     weighted
    0.08
    Activations Density 0.009%

    No Known Activations