© 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. 70272
    Prev
    Next
    INDEX
    Explanations

    really

    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
    -chave
    -0.09
    -Pacific
    -0.08
    -major
    -0.08
     Pradesh
    -0.08
     commend
    -0.08
    四川
    -0.07
     esquer
    -0.07
    ologically
    -0.07
    лект
    -0.07
    hips
    -0.07
    POSITIVE LOGITS
     hire
    0.08
     하루
    0.07
     зн
    0.07
     bothered
    0.07
     läbi
    0.07
     veramente
    0.07
     ilusión
    0.07
     hel
    0.07
     surrounded
    0.07
     verdienen
    0.07
    Activations Density 0.022%

    No Known Activations