© 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. 23-RESID-POST-AA
    11. 51765
    Prev
    Next
    INDEX
    Explanations

    say "ay" ending

    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
    rok
    -0.09
    ANDING
    -0.09
    arm
    -0.09
    uzes
    -0.09
    ud
    -0.08
    ાર
    -0.08
     sl
    -0.08
    aks
    -0.08
    Zm
    -0.08
     exch
    -0.08
    POSITIVE LOGITS
    нәр
    0.09
    ค้า
    0.08
    VERTISEMENT
    0.08
    ctic
    0.08
    herence
    0.08
    vement
    0.08
    ividual
    0.08
    phanumeric
    0.08
    iconductor
    0.08
     ವಿಶೇಷ
    0.08
    Activations Density 0.018%

    No Known Activations