© 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. 22030
    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
     feelings
    -0.09
     еды
    -0.09
    -min
    -0.08
     эмо
    -0.08
     emoties
    -0.08
    \s
    -0.08
     sentimentos
    -0.08
     emotions
    -0.08
     Gefühle
    -0.08
    icky
    -0.08
    POSITIVE LOGITS
     कदम
    0.15
     bước
    0.15
    迈
    0.15
     مرحله
    0.15
     خطوة
    0.15
     مرحلة
    0.15
     આગળ
    0.15
     igbes
    0.14
     आगे
    0.14
    步
    0.14
    Activations Density 0.006%

    No Known Activations