© 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. 52127
    Prev
    Next
    INDEX
    Explanations

    气

    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
     Vitae
    -0.09
    ário
    -0.08
    రీ
    -0.08
     Tommy
    -0.08
    ød
    -0.08
     lear
    -0.08
     biaya
    -0.08
     Apprentice
    -0.08
     Lehr
    -0.08
    ÁRIO
    -0.08
    POSITIVE LOGITS
    象
    0.12
    wek
    0.08
     subs
    0.08
    ational
    0.07
    ub
    0.07
    HAN
    0.07
     statistical
    0.07
    希
    0.07
    agrams
    0.07
     impormasyon
    0.07
    Activations Density 0.001%

    No Known Activations