© 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. 48126
    Prev
    Next
    INDEX
    Explanations

    cultural influences

    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
     לד
    -0.09
     xs
    -0.09
     մանր
    -0.08
     badkamer
    -0.08
     жижиг
    -0.08
     ezigbo
    -0.08
     сайн
    -0.08
     一号
    -0.07
     nating
    -0.07
     dotted
    -0.07
    POSITIVE LOGITS
     influences
    0.20
     French
    0.17
     German
    0.16
     immigrants
    0.16
     European
    0.16
     immigrant
    0.16
     influence
    0.15
     Influ
    0.15
    Influ
    0.15
     immigration
    0.15
    Activations Density 0.038%

    No Known Activations