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. 103987
    Prev
    Next
    INDEX
    Explanations

    rational

    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
     او
    -0.08
     bor
    -0.07
     blackjack
    -0.07
     bleak
    -0.07
     mê
    -0.07
     braz
    -0.07
    .bold
    -0.07
    Barcode
    -0.07
     or
    -0.07
     bygg
    -0.07
    POSITIVE LOGITS
     restructure
    0.09
    úst
    0.08
     trik
    0.08
    encio
    0.08
    ذف
    0.08
    Jesu
    0.08
     sid
    0.08
     सूत्र
    0.08
     Pamp
    0.08
     преобраз
    0.08
    Activations Density 0.039%

    No Known Activations