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. 78635
    Prev
    Next
    INDEX
    Explanations

    Code/app development

    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
    792
    -0.08
    822
    -0.08
     Stratford
    -0.08
     vulnerabilities
    -0.08
     dehydration
    -0.08
     countless
    -0.08
     scorching
    -0.08
     vulnerability
    -0.08
     Πρό
    -0.07
     drywall
    -0.07
    POSITIVE LOGITS
     Bottom
    0.10
    Bottom
    0.09
     bottom
    0.09
     destinations
    0.09
    ahrer
    0.09
     icon
    0.09
    Favorites
    0.09
     bottoms
    0.08
     restless
    0.08
    Icon
    0.08
    Activations Density 0.004%

    No Known Activations