© 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. 109825
    Prev
    Next
    INDEX
    Explanations

    wash

    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
    Negative Logits
    hift
    -0.08
    shift
    -0.08
    -fe
    -0.08
     Shift
    -0.07
     rigorous
    -0.07
    ijn
    -0.07
    _shift
    -0.07
    occ
    -0.07
     SHIFT
    -0.07
     بە
    -0.07
    POSITIVE LOGITS
     obligación
    0.09
     garantizar
    0.09
     tarea
    0.08
     cable
    0.08
     gereken
    0.08
     zekerheid
    0.08
     obligation
    0.08
    份
    0.08
     opges
    0.07
     venc
    0.07
    Activations Density 0.018%

    No Known Activations