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. 111980
    Prev
    Next
    INDEX
    Explanations

    lists and tables

    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
     না
    -0.08
     ಕೇಳ
    -0.07
     reg
    -0.07
    stitution
    -0.07
    asks
    -0.07
     }{@
    -0.07
     none
    -0.06
    ationale
    -0.06
     !=
    -0.06
     \↵
    -0.06
    POSITIVE LOGITS
     twins
    0.10
     Twins
    0.09
     serbisyo
    0.09
     lastly
    0.09
     Bazaar
    0.08
     Lastly
    0.08
     hum
    0.08
     tw
    0.08
     billi
    0.08
    /sw
    0.08
    Activations Density 0.126%

    No Known Activations