© 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. 110492
    Prev
    Next
    INDEX
    Explanations

    Multiple languages and code

    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
     glauben
    -0.08
     bẹ
    -0.08
    .Formatting
    -0.08
    废
    -0.07
    bracht
    -0.07
     bè
    -0.07
    /assert
    -0.07
     Texte
    -0.07
     relying
    -0.07
    余
    -0.07
    POSITIVE LOGITS
    Individuals
    0.08
     kam
    0.08
     lows
    0.07
     Italian
    0.07
     Kenyan
    0.07
     ambassadors
    0.07
     luc
    0.07
     tüü
    0.07
    Italian
    0.07
     descuento
    0.07
    Activations Density 0.001%

    No Known Activations