© 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 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. 19792
    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
    barcode
    -0.09
     environment
    -0.09
     content
    -0.08
     will
    -0.08
     schema
    -0.08
     daerah
    -0.08
     is
    -0.08
     datas
    -0.08
     color
    -0.08
     dạng
    -0.08
    POSITIVE LOGITS
     WWII
    0.21
    战争
    0.19
     युद्ध
    0.18
     الحرب
    0.18
     войны
    0.18
     oorlog
    0.15
     guerras
    0.14
     যুদ্ধ
    0.14
    -era
    0.14
     wars
    0.13
    Activations Density 0.019%

    No Known Activations