© 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. 11-RESID-POST-AA
    11. 95367
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
     savoir
    -0.08
     urin
    -0.08
    classe
    -0.08
     Patricia
    -0.08
     Blur
    -0.08
    AÇÃO
    -0.07
    izers
    -0.07
    -FIRST
    -0.07
    <Character
    -0.07
     substances
    -0.07
    POSITIVE LOGITS
     outreach
    0.11
     speeches
    0.11
     conferences
    0.11
     venues
    0.11
     engagements
    0.11
    推广
    0.11
     keynote
    0.11
     webinars
    0.10
     Conferences
    0.10
     Outreach
    0.10
    Activations Density 0.099%

    No Known Activations