© 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. 18179
    Prev
    Next
    INDEX
    Explanations

    common phrases and idioms

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     प्रधानम
    -0.11
     მრ
    -0.10
     Nunaanni
    -0.10
     ಗ್ರಾಮದ
    -0.10
     Taamaattumik
    -0.10
     მრავალ
    -0.10
    久久久
    -0.09
    精品一区二区三区
    -0.09
    Башҡ
    -0.09
    久久久久
    -0.09
    POSITIVE LOGITS
    	to
    0.18
     to
    0.16
    to
    0.15
     иметь
    0.14
    (to
    0.14
     сделать
    0.13
     попасть
    0.12
     заниматься
    0.12
     להשתמש
    0.12
     mieć
    0.12
    Activations Density 0.025%

    No Known Activations