© 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. 19-RESID-POST-AA
    11. 18914
    Prev
    Next
    INDEX
    Explanations

    say time zone

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pihak
    -0.10
    finni
    -0.09
     gcuid
    -0.08
     defnydd
    -0.08
    inku
    -0.08
     lapho
    -0.08
    êmement
    -0.08
     gwamn
    -0.08
     entsprechenden
    -0.08
     Haar
    -0.08
    POSITIVE LOGITS
     year
    0.12
    _year
    0.11
    .year
    0.11
     సంవత్స
    0.11
     वर्ष
    0.10
    year
    0.10
     YEAR
    0.10
    ปี
    0.10
    Year
    0.10
     ವರ್ಷ
    0.09
    Activations Density 0.003%

    No Known Activations