© 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. 23-RESID-POST-AA
    11. 49453
    Prev
    Next
    INDEX
    Explanations

    B

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caric
    -0.08
    arkers
    -0.08
    ئر
    -0.08
     pushing
    -0.07
     crib
    -0.07
     melk
    -0.07
     butter
    -0.07
     تزيد
    -0.07
    ière
    -0.07
    ar
    -0.07
    POSITIVE LOGITS
    ento
    0.10
     Caller
    0.08
    ెంట
    0.08
    -owned
    0.08
     Madd
    0.08
    Caller
    0.08
    aked
    0.08
    ेंट
    0.08
    udd
    0.08
    entre
    0.07
    Activations Density 0.001%

    No Known Activations