© 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. 3-RESID-POST-AA
    11. 2893
    Prev
    Next
    INDEX
    Explanations

    Found footage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пол
    -0.08
    ounter
    -0.08
    권
    -0.07
     സ്ഥിര
    -0.07
    精
    -0.07
    人
    -0.07
     тир
    -0.07
    赖
    -0.07
     সৌ
    -0.07
     gels
    -0.07
    POSITIVE LOGITS
     Czech
    0.08
     wab
    0.08
     Raven
    0.07
     (;;)
    0.07
     Adoption
    0.07
    Looper
    0.07
     TEST
    0.07
     Stella
    0.07
    _SHARE
    0.07
    %e
    0.07
    Activations Density 0.000%

    No Known Activations