© 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. 15-RESID-POST-AA
    11. 16522
    Prev
    Next
    INDEX
    Explanations

    Foreign language

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cricao
    -0.08
     שמש
    -0.08
     שמ
    -0.08
    Ese
    -0.08
    masını
    -0.07
    ייח
    -0.07
     hoort
    -0.07
     geblieben
    -0.07
    uchen
    -0.07
     memper
    -0.07
    POSITIVE LOGITS
     للأطفال
    0.11
     противопоказ
    0.10
     incompatible
    0.10
     pregnant
    0.10
     wegens
    0.10
     بالقرب
    0.09
     vicino
    0.09
     لأول
    0.09
     elderly
    0.09
    .disabled
    0.09
    Activations Density 0.019%

    No Known Activations