© 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. 109812
    Prev
    Next
    INDEX
    Explanations

    script dialogues

    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
     subsidies
    -0.08
    _connected
    -0.08
    .getenv
    -0.08
     সংবাদ
    -0.08
     econômico
    -0.08
     플랫폼
    -0.08
     Subsid
    -0.08
     Pope
    -0.08
    .solution
    -0.08
    μος
    -0.07
    POSITIVE LOGITS
     hypnot
    0.14
     hypnosis
    0.13
     misch
    0.12
     sedation
    0.10
     BDSM
    0.09
     эксперимент
    0.09
     ritual
    0.09
     magician
    0.09
    experiment
    0.09
     experiment
    0.09
    Activations Density 0.033%

    No Known Activations