Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 49464
    Prev
    Next
    INDEX
    Explanations

    instructions and deletion

    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
     rainfall
    -0.08
    .wicket
    -0.08
     shock
    -0.07
     organic
    -0.07
     وان
    -0.07
    .Color
    -0.07
    .bet
    -0.07
     வ
    -0.07
    181
    -0.07
     fluctuations
    -0.07
    POSITIVE LOGITS
    omy
    0.09
    mee
    0.08
     Favorites
    0.08
    avors
    0.08
     kalau
    0.08
     lifecycle
    0.08
    _confirmation
    0.08
    _CONFIRM
    0.08
     Carn
    0.08
     `"
    0.08
    Activations Density 0.001%

    No Known Activations