© 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. 19-RESID-POST-AA
    11. 22209
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mediation
    -0.08
     באמצ
    -0.07
    IRS
    -0.07
    AAF
    -0.07
     withholding
    -0.07
     neurological
    -0.07
    Toggle
    -0.07
     even
    -0.07
    <ll
    -0.07
     centrally
    -0.07
    POSITIVE LOGITS
     Which
    0.09
     eset
    0.09
     yang
    0.08
     SUCH
    0.08
     Probability
    0.08
     takich
    0.08
     وخاصة
    0.08
    -अलग
    0.08
    ות
    0.08
     Probably
    0.08
    Activations Density 0.000%

    No Known Activations