© 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. 22921
    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
    Negative Logits
     означает
    -0.09
    	num
    -0.09
    	size
    -0.09
     म्हणजे
    -0.09
     是
    -0.08
     يوجد
    -0.08
     thirty
    -0.08
    .num
    -0.08
     Means
    -0.08
     అంటే
    -0.08
    POSITIVE LOGITS
     some
    0.12
     then
    0.10
     일부
    0.10
     the
    0.10
     luego
    0.09
     vervolgens
    0.09
     totalité
    0.09
     이후
    0.09
     their
    0.09
     everything
    0.09
    Activations Density 0.049%

    No Known Activations