© 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. 19537
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     percentual
    -0.09
     porcentaje
    -0.08
     percent
    -0.08
     dominante
    -0.08
    走势
    -0.08
    domin
    -0.08
     ശതമ
    -0.08
     aşk
    -0.08
     শতাংশ
    -0.08
     प्रतिशत
    -0.08
    POSITIVE LOGITS
     المعدات
    0.32
     تجهیزات
    0.32
     equipment
    0.30
     معدات
    0.29
     kagamitan
    0.29
     equipamentos
    0.29
     équipements
    0.29
     Ausstattung
    0.28
     Equipment
    0.27
    装备
    0.27
    Activations Density 0.220%

    No Known Activations