© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64405
    Prev
    Next
    INDEX
    Explanations

    Instructions and advice

    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
     unfortunately
    -0.09
     strangely
    -0.09
     sadly
    -0.08
     leider
    -0.08
    lebih
    -0.08
     कथ
    -0.08
     Must
    -0.08
     Warum
    -0.08
    .history
    -0.07
     warum
    -0.07
    POSITIVE LOGITS
    正确
    0.15
    Correct
    0.12
     correctement
    0.12
     correctly
    0.12
     correcta
    0.12
     correctamente
    0.12
     correct
    0.12
     properly
    0.12
    充分
    0.11
     adequately
    0.11
    Activations Density 0.190%

    No Known Activations