© 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. 50056
    Prev
    Next
    INDEX
    Explanations

    say "2"

    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
     ildə
    -0.08
     uren
    -0.08
     Wird
    -0.08
     keçiril
    -0.08
     Heinrich
    -0.08
     புக
    -0.08
     fama
    -0.08
     tax
    -0.07
    lec
    -0.07
     XII
    -0.07
    POSITIVE LOGITS
    ick
    0.08
    UJ
    0.08
    DIR
    0.08
    orette
    0.08
    OR
    0.07
    CS
    0.07
    RS
    0.07
     अंग
    0.07
    IDGE
    0.07
    erase
    0.07
    Activations Density 0.001%

    No Known Activations