Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23740
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taxpayer
    -0.09
     subsidi
    -0.09
     saham
    -0.09
     工
    -0.08
     зарп
    -0.08
    窍
    -0.08
     ọrụ
    -0.08
     nyere
    -0.08
    文章
    -0.08
     depos
    -0.08
    POSITIVE LOGITS
     Welcome
    0.12
     Begegn
    0.12
     encounter
    0.11
    Welcome
    0.11
     Encounter
    0.11
    Interactive
    0.11
    Interact
    0.11
     Gameplay
    0.11
    Gameplay
    0.10
     Interactive
    0.10
    Activations Density 0.018%

    No Known Activations