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. 43335
    Prev
    Next
    INDEX
    Explanations

    ann

    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
     plugins
    -0.08
     standards
    -0.07
    plugins
    -0.07
     hany
    -0.07
    UTF
    -0.07
    роп
    -0.07
     signals
    -0.07
     commands
    -0.07
     individualized
    -0.07
     immersive
    -0.07
    POSITIVE LOGITS
     ácido
    0.09
    奸
    0.09
     ruthless
    0.09
     arrogant
    0.09
     mole
    0.08
     infamous
    0.08
     sly
    0.08
    .ai
    0.08
     sarcas
    0.08
     đỏ
    0.08
    Activations Density 0.004%

    No Known Activations