© 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. 23103
    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
     protagonist
    -0.09
     первом
    -0.08
    पह
    -0.08
     protagonista
    -0.08
     पहला
    -0.08
     protagonists
    -0.08
     первый
    -0.07
    ations
    -0.07
    изнес
    -0.07
    -first
    -0.07
    POSITIVE LOGITS
     ikinci
    0.11
     দ্বিত
    0.11
     രണ്ടാം
    0.11
     দ্বিতীয়
    0.11
     второго
    0.11
     השני
    0.10
    (second
    0.10
     tweede
    0.10
     secundarios
    0.10
     второй
    0.10
    Activations Density 2.699%

    No Known Activations