© 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. 113458
    Prev
    Next
    INDEX
    Explanations

    sight words

    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
     introd
    -0.08
     tahap
    -0.08
     introduction
    -0.08
     gifs
    -0.08
     rense
    -0.08
     introducing
    -0.08
     Sven
    -0.08
    γε
    -0.08
    icí
    -0.07
     gif
    -0.07
    POSITIVE LOGITS
    napshot
    0.08
    Shot
    0.08
    _rec
    0.08
    _metric
    0.08
    Warp
    0.07
     Medina
    0.07
    не
    0.07
     Format
    0.07
    Safe
    0.07
    -worthy
    0.07
    Activations Density 0.005%

    No Known Activations