© 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. 11-RESID-POST-AA
    11. 44764
    Prev
    Next
    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मध्य
    -0.09
     ಮಧ್ಯ
    -0.08
    _EP
    -0.08
    eed
    -0.08
    त्या
    -0.08
    hava
    -0.08
     partitions
    -0.08
     माध्यम
    -0.08
    cycles
    -0.08
     મધ
    -0.08
    POSITIVE LOGITS
    Translated
    0.11
    Translate
    0.11
     untranslated
    0.10
    Translation
    0.10
     번
    0.10
     translation
    0.10
     tradução
    0.10
     traduc
    0.10
    翻
    0.10
     translations
    0.10
    Activations Density 0.063%

    No Known Activations