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. 109992
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     complies
    -0.10
    规定
    -0.09
     complying
    -0.09
    遵
    -0.08
    -0.08
    Orientation
    -0.08
     comply
    -0.08
     adhesives
    -0.08
    投诉
    -0.08
    ’où
    -0.08
    POSITIVE LOGITS
     predicting
    0.12
     예상
    0.11
     speculative
    0.10
     прогноз
    0.10
     attacking
    0.10
     imminent
    0.10
     predictions
    0.09
    预测
    0.09
     estim
    0.09
     contender
    0.09
    Activations Density 0.184%

    No Known Activations