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. 111530
    Prev
    Next
    INDEX
    Explanations

    Chinese context

    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
    ถูก
    -0.09
     empfind
    -0.08
     stát
    -0.08
    ρίες
    -0.08
     امن
    -0.08
    หนึ่ง
    -0.08
     വിവര
    -0.08
     σύν
    -0.08
     fertile
    -0.08
     요구
    -0.08
    POSITIVE LOGITS
    落实
    0.09
    习近平
    0.09
    ,加强
    0.08
     urgently
    0.08
     constipation
    0.08
    Jpa
    0.08
    贯彻
    0.08
     lia
    0.08
    开展
    0.07
     genoten
    0.07
    Activations Density 0.029%

    No Known Activations