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. 113970
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Renee
    -0.09
     breaks
    -0.09
     действия
    -0.08
     BREAK
    -0.08
     asupra
    -0.08
    vap
    -0.08
    endida
    -0.08
     Litigation
    -0.07
     اتجاه
    -0.07
     делать
    -0.07
    POSITIVE LOGITS
     prestigious
    0.10
    MIT
    0.08
     MIT
    0.08
     reputable
    0.08
     Xt
    0.08
     parlament
    0.08
     mathematic
    0.08
     Cornell
    0.08
    <?>
    0.08
     gesammelt
    0.08
    Activations Density 0.007%

    No Known Activations