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. 12668
    Prev
    Next
    INDEX
    Explanations

    Uncertainty

    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
     steadily
    -0.08
     uitge
    -0.08
     synthesis
    -0.08
     prospect
    -0.08
     reduces
    -0.08
    [...]↵↵
    -0.08
    ___
    -0.07
    .'↵↵
    -0.07
    я
    -0.07
    X
    -0.07
    POSITIVE LOGITS
     самом
    0.09
     trouwens
    0.08
     ثق
    0.08
     القي
    0.08
    -benar
    0.07
     subtle
    0.07
     Davies
    0.07
     beso
    0.07
     юрид
    0.07
     안전
    0.07
    Activations Density 0.088%

    No Known Activations