© 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. 11-RESID-POST-AA
    11. 71484
    Prev
    Next
    INDEX
    Explanations

    Holland

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strong
    -0.08
     strong
    -0.08
     Larsen
    -0.07
     Aless
    -0.07
     Tiv
    -0.07
     Seen
    -0.07
     Strong
    -0.07
    �
    -0.07
     Sullivan
    -0.07
     Blum
    -0.07
    POSITIVE LOGITS
    Cha
    0.08
    Avatar
    0.08
    න්ත
    0.08
     trot
    0.08
     знак
    0.08
    єї
    0.08
     одном
    0.08
     procès
    0.08
     이동
    0.08
    Profession
    0.08
    Activations Density 0.018%

    No Known Activations