© 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. 23-RESID-POST-AA
    11. 48005
    Prev
    Next
    INDEX
    Explanations

    non-English and code snippets

    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
    ной
    -0.16
    ционной
    -0.14
    ственной
    -0.13
    альной
    -0.13
    чной
    -0.12
    ической
    -0.11
    енной
    -0.11
    ительной
    -0.11
    очной
    -0.11
    ированной
    -0.11
    POSITIVE LOGITS
    ый
    0.13
    า
    0.11
    ский
    0.11
    ம்
    0.11
    ం
    0.11
    ка
    0.10
    ика
    0.10
    ย์
    0.10
    ный
    0.10
    ие
    0.10
    Activations Density 0.044%

    No Known Activations