© 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. 102636
    Prev
    Next
    INDEX
    Explanations

    Discipline

    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
     caching
    -0.08
     verão
    -0.08
     glowing
    -0.08
    Caching
    -0.08
    Locales
    -0.07
    jší
    -0.07
    ummer
    -0.07
     glossy
    -0.07
     rooftop
    -0.07
     ενη
    -0.07
    POSITIVE LOGITS
    纪律
    0.40
     дисцип
    0.40
     discipline
    0.39
     disciplina
    0.38
     Discipline
    0.38
     disciplined
    0.37
     disciplin
    0.34
    discip
    0.33
     disciplines
    0.32
     disciplinary
    0.32
    Activations Density 0.030%

    No Known Activations