© 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. 5444
    Prev
    Next
    INDEX
    Explanations

    reason

    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
     réalisées
    -0.10
     réalisés
    -0.10
     آسی
    -0.09
     realitat
    -0.09
     აქ
    -0.09
     ისეთი
    -0.09
    ირდ
    -0.09
     хүрт
    -0.09
     ისეთ
    -0.09
    დნენ
    -0.09
    POSITIVE LOGITS
     why
    0.26
     waarom
    0.21
     warum
    0.20
    Why
    0.20
    why
    0.19
     Why
    0.19
    为什么
    0.18
     behind
    0.17
     WHY
    0.17
    为何
    0.17
    Activations Density 0.039%

    No Known Activations