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

    Neuronpedia

    Jacobian LensNEW
    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. 69529
    Prev
    Next
    INDEX
    Explanations

    primers

    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
     apprenticeship
    -0.08
     stave
    -0.08
    jin
    -0.08
     Reputation
    -0.08
    Award
    -0.08
     VALUE
    -0.07
     awards
    -0.07
     reputation
    -0.07
     Award
    -0.07
     Monet
    -0.07
    POSITIVE LOGITS
     primers
    0.12
     pair
    0.09
     pairs
    0.09
     Directions
    0.09
     направ
    0.09
     directions
    0.08
    _coordinates
    0.08
     flank
    0.08
    _pair
    0.08
     producteurs
    0.08
    Activations Density 0.002%

    No Known Activations