© 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. 18023
    Prev
    Next
    INDEX
    Explanations

    Names in movie production

    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
     latter
    -0.10
     ಎಲ್ಲಾ
    -0.09
     soit
    -0.09
     presumably
    -0.09
    1
    -0.09
     બધા
    -0.09
     ನಾವು
    -0.09
     hence
    -0.09
     ಯಾವುದೇ
    -0.09
     same
    -0.09
    POSITIVE LOGITS
     "
    0.08
     Flynn
    0.08
    Verder
    0.08
     Welke
    0.08
    ожа
    0.08
     көр
    0.08
     Lomb
    0.08
    �讯
    0.08
     How
    0.08
     Tutt
    0.08
    Activations Density 0.040%

    No Known Activations