© 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. 25085
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Nih
    -0.08
     ở
    -0.08
     dehydr
    -0.08
    ətin
    -0.08
    NK
    -0.07
    Trend
    -0.07
     Depp
    -0.07
    본
    -0.07
     nurses
    -0.07
     chickens
    -0.07
    POSITIVE LOGITS
    面积
    0.08
     bagi
    0.08
    .area
    0.08
     व्याप
    0.08
     QRect
    0.08
    .idx
    0.08
    	rect
    0.08
     bounding
    0.08
     rect
    0.08
     uuid
    0.07
    Activations Density 0.026%

    No Known Activations