© 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. 45650
    Prev
    Next
    INDEX
    Explanations

    Drawing grids/graphics

    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
     phrase
    -0.08
    zeda
    -0.08
    기사
    -0.08
     لدى
    -0.08
     Roche
    -0.08
     marketing
    -0.07
    okay
    -0.07
    marketing
    -0.07
    phrase
    -0.07
     Moderna
    -0.07
    POSITIVE LOGITS
     grid
    0.14
    .grid
    0.14
    (grid
    0.13
     Grid
    0.12
    _grid
    0.12
     grids
    0.12
    Grid
    0.12
    	grid
    0.12
    -grid
    0.11
    <Grid
    0.11
    Activations Density 0.012%

    No Known Activations