© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ure/-ur"

    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
     Citizen
    -0.08
     Size
    -0.08
     Orientation
    -0.08
     biomedical
    -0.08
    籍
    -0.08
    _zoom
    -0.08
     Biomedical
    -0.08
    注文
    -0.08
     Elli
    -0.07
     zoom
    -0.07
    POSITIVE LOGITS
    igkeits
    0.16
     воздуха
    0.15
     moisture
    0.13
     влаг
    0.13
     humidity
    0.13
     humedad
    0.12
    humidity
    0.11
     الهواء
    0.11
    Content
    0.11
     воздух
    0.11
    Activations Density 0.016%

    No Known Activations