© 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. 110059
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
     приглаш
    -0.08
    ibre
    -0.08
     haa
    -0.08
     kwuru
    -0.07
     relasyon
    -0.07
    **)(&
    -0.07
    сиа
    -0.07
     jotka
    -0.07
    KHR
    -0.07
    Msg
    -0.07
    POSITIVE LOGITS
     deviations
    0.09
     asym
    0.08
     slightly
    0.08
     discrepancy
    0.08
     deviation
    0.08
    forced
    0.08
     discrepancies
    0.08
    ponsive
    0.08
    acions
    0.07
    hel
    0.07
    Activations Density 0.002%

    No Known Activations