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. 103272
    Prev
    Next
    INDEX
    Explanations

    .

    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
     Napoleon
    -0.07
     entry
    -0.07
     Min
    -0.07
     AW
    -0.07
     action
    -0.07
     onder
    -0.07
    Msg
    -0.07
     comprehensive
    -0.07
     number
    -0.06
     EXIT
    -0.06
    POSITIVE LOGITS
     discrepancy
    0.10
     ternyata
    0.09
     superfic
    0.09
    Incorrect
    0.09
     terribly
    0.09
     incorrectly
    0.09
     incorrect
    0.09
     тракт
    0.09
     encountered
    0.08
     Incorrect
    0.08
    Activations Density 0.093%

    No Known Activations