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. 111759
    Prev
    Next
    INDEX
    Explanations

    Arbitrary word lists

    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
    ='.
    -0.08
     bölüm
    -0.07
     നടത്തുന്ന
    -0.07
     ".$
    -0.07
    =".
    -0.07
     subsection
    -0.07
     terá
    -0.07
     لديها
    -0.07
    针对
    -0.07
    RESS
    -0.07
    POSITIVE LOGITS
    усов
    0.08
     tom
    0.08
    лан
    0.07
    күн
    0.07
     tôt
    0.07
    іл
    0.07
     kindergarten
    0.07
     Mous
    0.07
     свой
    0.07
     obligated
    0.07
    Activations Density 0.019%

    No Known Activations