© 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 EvalsExportsinterp-engineNEWAPI 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. 71190
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions

    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
     Hul
    -0.07
     Red
    -0.07
     temporal
    -0.07
    晋
    -0.07
     Hap
    -0.07
     năng
    -0.07
     Lut
    -0.07
     Li
    -0.07
     red
    -0.07
     spaz
    -0.07
    POSITIVE LOGITS
    Singles
    0.08
    环球
    0.08
    obe
    0.08
     maailman
    0.08
     donar
    0.08
    .Supplier
    0.08
     mappings
    0.08
    Server
    0.08
    薄
    0.08
    zela
    0.08
    Activations Density 0.009%

    No Known Activations