© 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. 18067
    Prev
    Next
    INDEX
    Explanations

    +

    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
     압
    -0.08
    **
    -0.07
     {}
    -0.07
    *
    -0.07
     맞
    -0.06
     ratio
    -0.06
    ------
    -0.06
    ológ
    -0.06
     행동
    -0.06
     मतलब
    -0.06
    POSITIVE LOGITS
     fijo
    0.11
    Known
    0.11
    known
    0.11
     wakhe
    0.11
     bekannten
    0.10
     known
    0.10
     diketahui
    0.10
    gegeben
    0.10
     conhecido
    0.10
     knowing
    0.10
    Activations Density 0.095%

    No Known Activations