© 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. 110000
    Prev
    Next
    INDEX
    Explanations

    extreme conditions

    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
     Myst
    -0.08
    stata
    -0.08
    parcel
    -0.08
     LET
    -0.08
    Myst
    -0.08
    (exp
    -0.08
    enames
    -0.07
     tum
    -0.07
     Wanted
    -0.07
    deliver
    -0.07
    POSITIVE LOGITS
     extremes
    0.12
     extremos
    0.09
     suhu
    0.08
     искусства
    0.08
    情况下
    0.08
     不
    0.08
     ekstrem
    0.07
    فعال
    0.07
    玩
    0.07
     mínimos
    0.07
    Activations Density 0.009%

    No Known Activations