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. 103300
    Prev
    Next
    INDEX
    Explanations

    REM sleep

    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
     cumbersome
    -0.08
     Transactions
    -0.08
    _ACCEPT
    -0.07
    乡
    -0.07
    272
    -0.07
    _abs
    -0.07
    .top
    -0.07
     ér
    -0.07
    ıt
    -0.07
    приєм
    -0.07
    POSITIVE LOGITS
     producing
    0.08
     быть
    0.07
     إنتاج
    0.07
     حقوق
    0.07
     hoog
    0.07
     produz
    0.07
     выдел
    0.07
     удел
    0.07
     jockey
    0.07
     oph
    0.07
    Activations Density 0.002%

    No Known Activations