© 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. 71708
    Prev
    Next
    INDEX
    Explanations

    big

    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
     ofens
    -0.09
    దేశ
    -0.08
    /home
    -0.07
     brut
    -0.07
    *"
    -0.07
     bruto
    -0.07
     contaminated
    -0.07
     Offensive
    -0.07
    /Home
    -0.07
    (home
    -0.07
    POSITIVE LOGITS
     startled
    0.10
    睛
    0.09
     বড়
    0.09
     واسعة
    0.09
     учащ
    0.09
     entusiasmo
    0.09
     глаза
    0.09
     كبيرة
    0.09
    学习
    0.09
     oversized
    0.08
    Activations Density 0.011%

    No Known Activations