© 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. 19-RESID-POST-AA
    11. 102197
    Prev
    Next
    INDEX
    Explanations

    pregnancy and birth

    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
     discretionary
    -0.10
     американ
    -0.10
     경찰
    -0.09
     américain
    -0.09
     cynical
    -0.09
     미국
    -0.09
     estadounidense
    -0.09
     euro
    -0.09
     barato
    -0.09
    美国
    -0.09
    POSITIVE LOGITS
     newborn
    0.20
     childbirth
    0.20
     parto
    0.18
     motherhood
    0.17
     gravid
    0.17
     maternal
    0.17
     കുഞ്ഞ
    0.16
     grossesse
    0.16
     infants
    0.16
     fetal
    0.16
    Activations Density 0.045%

    No Known Activations