© 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. 18021
    Prev
    Next
    INDEX
    Explanations

    Representing digits with letters

    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
    last
    -0.09
     letzten
    -0.09
    Last
    -0.08
     sidste
    -0.08
     Last
    -0.08
    -last
    -0.08
     posled
    -0.08
     letz
    -0.08
    tra
    -0.08
     letzte
    -0.08
    POSITIVE LOGITS
     médicale
    0.09
     adaptée
    0.09
    ديه
    0.09
     медицина
    0.09
     adapted
    0.08
     naming
    0.08
     თანამედროვე
    0.08
     الإنجليزية
    0.08
     customized
    0.08
     letters
    0.08
    Activations Density 0.002%

    No Known Activations