© 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 EvalsExportsAPI 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. 50224
    Prev
    Next
    INDEX
    Explanations

    say "600"

    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
     näin
    -0.09
    'ng
    -0.09
     mer
    -0.08
    isieren
    -0.08
     divers
    -0.08
     diversification
    -0.08
     Mer
    -0.08
    Mer
    -0.08
    mer
    -0.08
    icl
    -0.08
    POSITIVE LOGITS
    .baidu
    0.08
     Ninja
    0.07
     ML
    0.07
    เว
    0.07
     лаборат
    0.07
     BI
    0.07
     Blade
    0.07
    ิบ
    0.07
     Automation
    0.07
    0.07
    Activations Density 0.001%

    No Known Activations