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. 12782
    Prev
    Next
    INDEX
    Explanations

    candle

    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
     mode
    -0.09
    _LOOK
    -0.08
     Outlet
    -0.08
    	mode
    -0.07
     Eugene
    -0.07
     pest
    -0.07
     Hamilton
    -0.07
    mode
    -0.07
     fmt
    -0.07
     sü
    -0.07
    POSITIVE LOGITS
    culator
    0.09
    PSD
    0.08
    pector
    0.08
     culturais
    0.08
     indican
    0.08
    Mover
    0.08
     culturales
    0.08
    Mob
    0.08
     bigger
    0.08
    Hill
    0.08
    Activations Density 0.001%

    No Known Activations