© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6459
    Prev
    Next
    INDEX
    Explanations

    .

    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
    oo
    -0.08
    -use
    -0.08
     disabling
    -0.08
     realizar
    -0.07
    표
    -0.07
     adaptations
    -0.07
    forcement
    -0.07
    -w
    -0.07
     Use
    -0.07
     USE
    -0.07
    POSITIVE LOGITS
    ੰਡ
    0.09
    Neighbours
    0.09
    Family
    0.08
     المنتدى
    0.08
     gegeten
    0.08
    Bookings
    0.08
     gallu
    0.08
     الوقت
    0.08
    (IDC
    0.08
    tranet
    0.08
    Activations Density 0.000%

    No Known Activations