© 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. 71402
    Prev
    Next
    INDEX
    Explanations

    relieving oneself

    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
     mito
    -0.09
    cement
    -0.08
     moi
    -0.08
    gau
    -0.08
    mö
    -0.08
     dynam
    -0.07
     gauge
    -0.07
     terrorismo
    -0.07
    faith
    -0.07
     toque
    -0.07
    POSITIVE LOGITS
    不得
    0.09
     (;;
    0.08
     leest
    0.08
     recount
    0.08
     Pourquoi
    0.08
    忍
    0.08
    Pourquoi
    0.08
    entesque
    0.08
    édients
    0.07
    уси
    0.07
    Activations Density 0.001%

    No Known Activations