© 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. 71514
    Prev
    Next
    INDEX
    Explanations

    bowel diseases

    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
    Yaw
    -0.08
     Keh
    -0.08
    �
    -0.08
     Sgt
    -0.08
     yau
    -0.08
     пяти
    -0.08
     эк
    -0.08
    Ug
    -0.08
     horas
    -0.08
     PSA
    -0.08
    POSITIVE LOGITS
     intermittent
    0.11
     intermitt
    0.10
     spor
    0.08
     occasional
    0.08
    (toggle
    0.08
     episod
    0.08
     polém
    0.08
     controvers
    0.08
     adicionales
    0.07
    restart
    0.07
    Activations Density 0.005%

    No Known Activations