© 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. 15-RESID-POST-AA
    11. 16468
    Prev
    Next
    INDEX
    Explanations

    out

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    掲
    -0.08
     Down
    -0.08
     создания
    -0.08
     डाउन
    -0.07
    下来
    -0.07
     farewell
    -0.07
     cérémonie
    -0.07
    'appel
    -0.07
    (New
    -0.07
     দেখা
    -0.07
    POSITIVE LOGITS
     máximo
    0.09
    更多
    0.09
     conteúdos
    0.08
     maximal
    0.08
     المزيد
    0.08
     características
    0.08
     maksimal
    0.08
     ಹೆಚ್ಚಿನ
    0.08
     detalhes
    0.08
    Extract
    0.08
    Activations Density 0.006%

    No Known Activations