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. 102931
    Prev
    Next
    INDEX
    Explanations

    Chinese text

    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
     என்பது
    -0.09
     Kh
    -0.09
     eget
    -0.08
     hierbei
    -0.08
    Useful
    -0.08
     Lazy
    -0.08
    anno
    -0.08
     또한
    -0.07
    368
    -0.07
     merupakan
    -0.07
    POSITIVE LOGITS
    进行
    0.14
    找到
    0.11
    整理
    0.11
    进行了
    0.11
    展开
    0.10
    保持
    0.10
    获得
    0.10
    推出
    0.10
     nweta
    0.10
     இருந்து
    0.10
    Activations Density 0.093%

    No Known Activations