© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17939
    Prev
    Next
    INDEX
    Explanations

    При

    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
    Negative Logits
     בדיוק
    -0.09
     דווקא
    -0.08
     �
    -0.08
     עם
    -0.08
     ←
    -0.08
     הוא
    -0.08
     בעיקר
    -0.08
     活
    -0.07
     οι
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    оритет
    0.14
     этом
    0.14
    ницип
    0.14
    обрет
    0.12
     гэтым
    0.12
    нимать
    0.12
     выборе
    0.11
     цьому
    0.11
    ષ્�
    0.11
    нима
    0.11
    Activations Density 0.003%

    No Known Activations