© 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. 23-RESID-POST-AA
    11. 50728
    Prev
    Next
    INDEX
    Explanations

    say "door"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    формация
    -0.09
    enschap
    -0.09
    된
    -0.08
     asserted
    -0.08
     السلطات
    -0.08
    tted
    -0.08
    isiúnta
    -0.08
    роў
    -0.07
    истра
    -0.07
    ترف
    -0.07
    POSITIVE LOGITS
    《
    0.09
     『
    0.08
     《
    0.08
     ARG
    0.08
    ggj
    0.08
     plain
    0.08
     Ys
    0.08
     oy
    0.08
     fãs
    0.08
     sims
    0.07
    Activations Density 0.025%

    No Known Activations