© 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. 47811
    Prev
    Next
    INDEX
    Explanations

    owner

    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
    uma
    -0.08
     Bildungs
    -0.07
     immigrants
    -0.07
     mol
    -0.07
     molts
    -0.07
     Flash
    -0.07
     jum
    -0.07
     homo
    -0.07
    _concat
    -0.07
     Werbung
    -0.07
    POSITIVE LOGITS
     Verantwort
    0.11
     ответственности
    0.11
     responsibilities
    0.11
    负责人
    0.11
    落实
    0.11
    责任
    0.11
    负责
    0.10
     assignments
    0.10
    assign
    0.09
     enforcement
    0.09
    Activations Density 0.012%

    No Known Activations