© 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. 102999
    Prev
    Next
    INDEX
    Explanations

    household chores

    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
    .cert
    -0.08
    .jwt
    -0.07
     analy
    -0.07
    jwt
    -0.07
     viajar
    -0.07
    释
    -0.07
     passport
    -0.07
    .JWT
    -0.07
     journey
    -0.07
    Issuer
    -0.07
    POSITIVE LOGITS
     chores
    0.33
     huishoud
    0.24
     Haushalt
    0.24
     household
    0.24
     tarefas
    0.24
     tareas
    0.23
     tâches
    0.23
     huish
    0.22
     Household
    0.22
    _tasks
    0.21
    Activations Density 0.110%

    No Known Activations