© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Pope
    -0.09
     vaccine
    -0.09
     Pfizer
    -0.09
     inoc
    -0.09
     reproductive
    -0.09
     मानव
    -0.09
     humane
    -0.08
     सामाजिक
    -0.08
     moral
    -0.08
     인간
    -0.08
    POSITIVE LOGITS
    变化
    0.13
     שינוי
    0.12
    -change
    0.11
     փոփոխ
    0.11
     değiş
    0.11
     Veränder
    0.11
    不停
    0.11
     pagbab
    0.11
     변화
    0.11
     تبدیلی
    0.11
    Activations Density 0.002%

    No Known Activations