© 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. 102888
    Prev
    Next
    INDEX
    Explanations

    orders and decrees

    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
    ierre
    -0.08
    ¸
    -0.08
     bijdrage
    -0.08
     ê
    -0.08
    ညာ
    -0.08
     Buzz
    -0.08
    -0.07
     uptake
    -0.07
     professionals
    -0.07
    êmica
    -0.07
    POSITIVE LOGITS
    巡视
    0.16
     overseeing
    0.15
     personally
    0.14
     personalmente
    0.14
     decree
    0.13
     oversee
    0.13
     deleg
    0.13
     oversees
    0.13
     commands
    0.13
     gobier
    0.13
    Activations Density 0.097%

    No Known Activations