© 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. 23-RESID-POST-AA
    11. 52167
    Prev
    Next
    INDEX
    Explanations

    say werden

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    қи
    -0.09
    sprekend
    -0.09
    väl
    -0.09
    муш
    -0.09
    қу
    -0.08
    ಕ್ತಿ
    -0.08
    қс
    -0.08
    lles
    -0.08
    matụ
    -0.08
    lijkse
    -0.08
    POSITIVE LOGITS
     worden
    0.30
     werden
    0.27
     wird
    0.23
     wurde
    0.22
     wurden
    0.20
     wordt
    0.19
     werde
    0.16
     haben
    0.16
     bekommen
    0.16
     wurdt
    0.15
    Activations Density 0.011%

    No Known Activations