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. 29896
    Prev
    Next
    INDEX
    Explanations

    think

    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
     ####
    -0.07
     behaupt
    -0.07
    ιστα
    -0.07
     செய்யப்பட்ட
    -0.07
     ")
    -0.07
    .Assert
    -0.07
    Claims
    -0.07
     mint
    -0.07
    illustr
    -0.07
     motivate
    -0.07
    POSITIVE LOGITS
    ว่าจะ
    0.10
    最佳
    0.09
     optimal
    0.08
     بهترین
    0.08
     besar
    0.08
     tentang
    0.08
     về
    0.08
     najleps
    0.08
     mejores
    0.08
     Optimal
    0.08
    Activations Density 0.170%

    No Known Activations