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. 120296
    Prev
    Next
    INDEX
    Explanations

    a

    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
     stimulation
    -0.08
     avons
    -0.08
     VAR
    -0.07
     reproductive
    -0.07
    ну
    -0.07
    동안
    -0.07
     twijfel
    -0.07
     forensic
    -0.07
     warum
    -0.07
     variant
    -0.07
    POSITIVE LOGITS
     কাট
    0.10
    tered
    0.09
    editing
    0.09
     sanding
    0.08
     shaved
    0.08
     garnish
    0.08
     schu
    0.08
     polygons
    0.08
     polishing
    0.08
     nipples
    0.08
    Activations Density 0.016%

    No Known Activations