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. 90159
    Prev
    Next
    INDEX
    Explanations

    squares, geometry

    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
    RCT
    -0.08
    tablename
    -0.08
    出台
    -0.07
     جذب
    -0.07
    une
    -0.07
    .Table
    -0.07
    /get
    -0.07
    ITED
    -0.07
    حث
    -0.07
    pthread
    -0.07
    POSITIVE LOGITS
     rotated
    0.09
     verifying
    0.09
     Nassau
    0.09
    zier
    0.09
     idyllic
    0.08
    笔
    0.08
     kow
    0.08
    塘
    0.08
     luks
    0.08
    验
    0.08
    Activations Density 0.039%

    No Known Activations