© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110783
    Prev
    Next
    INDEX
    Explanations

    coding configurations

    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
     Cause
    -0.07
    cause
    -0.07
    ubuntu
    -0.07
    xxxx
    -0.07
     Put
    -0.07
    /Grid
    -0.07
    validation
    -0.06
     vask
    -0.06
    061
    -0.06
    mount
    -0.06
    POSITIVE LOGITS
     фестив
    0.09
    法人
    0.09
    르고
    0.09
    ণ
    0.08
     festival
    0.08
     FMC
    0.08
    ালী
    0.08
     бар
    0.08
    resident
    0.08
     festivals
    0.08
    Activations Density 0.000%

    No Known Activations