© 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. 109803
    Prev
    Next
    INDEX
    Explanations

    It's

    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
     indi
    -0.09
     venen
    -0.08
     certify
    -0.08
    esion
    -0.08
     Goldman
    -0.07
     लेकर
    -0.07
     લઈને
    -0.07
     repudi
    -0.07
    け
    -0.07
     samot
    -0.07
    POSITIVE LOGITS
     bastante
    0.08
     fairly
    0.08
     tricky
    0.08
    复杂
    0.08
     messy
    0.08
     довольно
    0.08
     conscientious
    0.08
    _complex
    0.07
    Seems
    0.07
     rutina
    0.07
    Activations Density 0.061%

    No Known Activations