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. 74584
    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
     towering
    -0.08
    perl
    -0.08
    .label
    -0.08
    prediction
    -0.08
    .pred
    -0.07
     label
    -0.07
     labels
    -0.07
     طويل
    -0.07
     labelled
    -0.07
     Prediction
    -0.07
    POSITIVE LOGITS
     convivial
    0.10
     amic
    0.09
     bridal
    0.09
     aesthetics
    0.09
     эстет
    0.09
     esposo
    0.08
     pleasant
    0.08
     estética
    0.08
     pleasing
    0.08
     ornamental
    0.08
    Activations Density 0.002%

    No Known Activations