© 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. 109993
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     adjud
    -0.09
    ansas
    -0.08
    ilg
    -0.08
     Gogh
    -0.08
     Craig
    -0.08
     Mitch
    -0.08
     unwavering
    -0.08
     Leap
    -0.08
    rook
    -0.08
     gallons
    -0.08
    POSITIVE LOGITS
     ukrain
    0.14
     Ukrainian
    0.13
    俄罗斯
    0.13
    В
    0.13
     СН
    0.13
     ГО
    0.13
    Для
    0.13
     РФ
    0.13
     с
    0.12
     В
    0.12
    Activations Density 2.576%

    No Known Activations