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. 77281
    Prev
    Next
    INDEX
    Explanations

    might

    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
     Pants
    -0.08
     radios
    -0.08
    .");↵
    -0.08
    TT
    -0.07
     footprint
    -0.07
     kait
    -0.07
     Radios
    -0.07
     Witt
    -0.07
     elo
    -0.07
     cogn
    -0.07
    POSITIVE LOGITS
    ाई
    0.08
     paj
    0.08
     מדובר
    0.08
     matter
    0.08
    ाइएको
    0.08
     लिया
    0.08
    (plan
    0.07
     ASC
    0.07
     Î
    0.07
     छोट
    0.07
    Activations Density 0.092%

    No Known Activations