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. 129867
    Prev
    Next
    INDEX
    Explanations

    operator

    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
    -0.07
     bluff
    -0.07
    -to
    -0.07
     Seh
    -0.07
     Resp
    -0.07
     aye
    -0.07
     resp
    -0.07
    (interface
    -0.07
     coz
    -0.07
     Rai
    -0.07
    POSITIVE LOGITS
    ="+
    0.09
     devastating
    0.08
     simpt
    0.08
     symbols
    0.08
    :"+
    0.08
    Algorithms
    0.08
     симптомы
    0.08
    operators
    0.08
     símbolos
    0.08
     debilitating
    0.08
    Activations Density 0.004%

    No Known Activations