© 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. 71707
    Prev
    Next
    INDEX
    Explanations

    icks

    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
     Pe
    -0.09
     extrad
    -0.08
     protr
    -0.08
     LOSS
    -0.08
     lois
    -0.07
     accepting
    -0.07
     electr
    -0.07
     kase
    -0.07
     Heath
    -0.07
    ‌ی
    -0.07
    POSITIVE LOGITS
    blend
    0.10
     blending
    0.09
     blended
    0.08
     blend
    0.08
     blends
    0.08
     ambientes
    0.08
     uncover
    0.07
    ways
    0.07
     Braun
    0.07
     hon
    0.07
    Activations Density 0.001%

    No Known Activations