© 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. 48575
    Prev
    Next
    INDEX
    Explanations

    behavior/behaviour

    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
    白菜
    -0.09
     kitchens
    -0.08
    -home
    -0.08
     kitchen
    -0.07
    -American
    -0.07
    built
    -0.07
    .appspot
    -0.07
     papier
    -0.07
    technic
    -0.07
     تجهیز
    -0.07
    POSITIVE LOGITS
     traits
    0.16
     Traits
    0.14
    Traits
    0.14
     atitudes
    0.14
     поведения
    0.14
     tendencies
    0.13
    態
    0.13
     davran
    0.13
     Verhalten
    0.13
     behaviors
    0.13
    Activations Density 0.066%

    No Known Activations