Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44116
    Prev
    Next
    INDEX
    Explanations

    matrix multiplication

    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
     наркот
    -0.09
     archaeology
    -0.08
     Arbitration
    -0.08
    指南
    -0.08
     gamblers
    -0.08
     людей
    -0.08
    安心
    -0.08
     myth
    -0.08
    在人
    -0.08
    戒
    -0.08
    POSITIVE LOGITS
    .Matrix
    0.16
    Transpose
    0.15
    	Matrix
    0.14
     matrices
    0.14
    (Matrix
    0.14
    Matrices
    0.14
    .transpose
    0.13
    (matrix
    0.13
     transpose
    0.13
    Matrix
    0.13
    Activations Density 0.014%

    No Known Activations