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. 61061
    Prev
    Next
    INDEX
    Explanations

    quotes and other languages

    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
    实力
    -0.09
    サイト
    -0.09
    対応
    -0.08
    .charset
    -0.08
    厂
    -0.08
    mith
    -0.08
     intimidated
    -0.08
    eland
    -0.07
    重量
    -0.07
    மான
    -0.07
    POSITIVE LOGITS
     expectancy
    0.10
     cotidiana
    0.10
     ജീവിത
    0.09
     lleno
    0.09
     véc
    0.09
     삶
    0.09
     intertw
    0.09
     intertwined
    0.09
     ಜೀವನ
    0.09
     حياة
    0.08
    Activations Density 0.108%

    No Known Activations