© 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. 110170
    Prev
    Next
    INDEX
    Explanations

    coding or running programs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     représ
    -0.09
     représentent
    -0.08
     turret
    -0.08
    łych
    -0.08
    突出
    -0.08
    итер
    -0.08
     বস
    -0.08
    เสียง
    -0.08
     tagata
    -0.08
     individualized
    -0.08
    POSITIVE LOGITS
    .use
    0.09
    (__
    0.08
    .__
    0.08
     journalists
    0.07
    .enable
    0.07
     ড
    0.07
     Rainbow
    0.07
     Journalism
    0.07
     use
    0.07
    (argc
    0.07
    Activations Density 0.079%

    No Known Activations