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. 65213
    Prev
    Next
    INDEX
    Explanations

    中

    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
    ‌ای
    -0.08
     를
    -0.08
    Som
    -0.08
     ताकि
    -0.07
    简称
    -0.07
    Crystal
    -0.07
    Smith
    -0.07
    MER
    -0.07
     అంటే
    -0.07
     скорости
    -0.07
    POSITIVE LOGITS
     থাকা
    0.09
    遣
    0.08
     olev
    0.08
    ിലെ
    0.08
    留下
    0.08
    有人
    0.07
     stigma
    0.07
    iro
    0.07
    里的
    0.07
    新增
    0.07
    Activations Density 0.017%

    No Known Activations