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. 58425
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
     infographic
    -0.08
     Perspective
    -0.08
     ప
    -0.08
     performer
    -0.08
    property
    -0.07
    ుల
    -0.07
    Optimize
    -0.07
    ulti
    -0.07
     chl
    -0.07
     missionaries
    -0.07
    POSITIVE LOGITS
     <-
    0.08
    .numeric
    0.08
     Middleware
    0.07
     vinter
    0.07
     Sydney
    0.07
    .Pattern
    0.07
     "...
    0.07
     (...
    0.07
    ánea
    0.07
     Ceiling
    0.07
    Activations Density 0.000%

    No Known Activations