© 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. 19-RESID-POST-AA
    11. 22752
    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
    ’autres
    -0.08
    	for
    -0.08
    'autres
    -0.08
    éticos
    -0.08
     mentions
    -0.08
    ítés
    -0.08
     akin
    -0.08
    аков
    -0.07
    stuff
    -0.07
    itionen
    -0.07
    POSITIVE LOGITS
     избавиться
    0.09
     соверш
    0.09
    定胆
    0.09
     לבצע
    0.09
    进行
    0.09
     დაამ
    0.09
     κάν
    0.09
    发送
    0.09
     Ҳа
    0.08
     Να
    0.08
    Activations Density 0.023%

    No Known Activations