© 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. 11-RESID-POST-AA
    11. 71623
    Prev
    Next
    INDEX
    Explanations

    init function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    цвет
    -0.07
     regulatory
    -0.07
     vérifier
    -0.07
    ారు
    -0.07
     Vér
    -0.07
     Regulatory
    -0.07
     List
    -0.07
     DP
    -0.07
     téléchargement
    -0.07
     essentiellement
    -0.07
    POSITIVE LOGITS
     perme
    0.08
    👏
    0.08
    γι
    0.08
     gurl
    0.07
     geme
    0.07
     perfor
    0.07
     behe
    0.07
     typo
    0.07
    َّ
    0.07
    0.07
    Activations Density 0.018%
    No Known Activations