© 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. 23-RESID-POST-AA
    11. 52105
    Prev
    Next
    INDEX
    Explanations

    пов

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ाए
    -0.08
    ie's
    -0.08
    ating
    -0.08
     promises
    -0.08
    ative
    -0.07
    atitis
    -0.07
     rep
    -0.07
     distracting
    -0.07
    ativo
    -0.07
    atement
    -0.07
    POSITIVE LOGITS
    едение
    0.11
    гоҳ
    0.09
    نه
    0.08
    通知
    0.08
    implicitly
    0.08
    артф
    0.08
     komp
    0.08
    едения
    0.08
    kwara
    0.08
    ്ഥ
    0.07
    Activations Density 0.000%

    No Known Activations