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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102897
    Prev
    Next
    INDEX
    Explanations

    ’m

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يدۇ
    -0.09
    ١
    -0.09
     χρόνια
    -0.09
     décide
    -0.08
     renouvel
    -0.08
     ευρώ
    -0.08
     Quelques
    -0.08
    ٧
    -0.08
     repeal
    -0.08
    envoud
    -0.08
    POSITIVE LOGITS
     आधारित
    0.14
     기반
    0.12
     running
    0.12
     based
    0.12
     ভিত্ত
    0.11
     basé
    0.11
     આધાર
    0.11
    _RUNNING
    0.11
     powered
    0.11
     baseado
    0.10
    Activations Density 0.003%

    No Known Activations