© 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. 54434
    Prev
    Next
    INDEX
    Explanations

    lesser-known things

    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
     veure
    -0.07
     verbind
    -0.07
     reger
    -0.07
     unrealistic
    -0.07
    В
    -0.07
     eight
    -0.07
     verniet
    -0.07
     begeleiding
    -0.07
     integrity
    -0.07
     verboden
    -0.07
    POSITIVE LOGITS
     lesser
    0.10
     عنه
    0.09
    -performing
    0.08
    -reviewed
    0.08
    _than
    0.08
    teva
    0.08
    perform
    0.08
     quieter
    0.08
     sludge
    0.07
     gems
    0.07
    Activations Density 0.031%

    No Known Activations