© 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. 111336
    Prev
    Next
    INDEX
    Explanations

    regression

    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
     faç
    -0.09
    ğun
    -0.08
     manifeste
    -0.08
     arrivé
    -0.08
     信
    -0.08
    ma
    -0.07
     downfall
    -0.07
     acaba
    -0.07
     ГО
    -0.07
    #!
    -0.07
    POSITIVE LOGITS
     rer
    0.10
    rer
    0.09
     uitgevoerd
    0.09
     durchgeführt
    0.09
    Performed
    0.09
     executed
    0.09
     durchführen
    0.08
    rios
    0.08
    Executed
    0.08
     routine
    0.08
    Activations Density 0.001%

    No Known Activations