© 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. 30988
    Prev
    Next
    INDEX
    Explanations

    inventions

    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
     Somali
    -0.08
     Markdown
    -0.07
     cortisol
    -0.07
     "~/
    -0.07
     moderated
    -0.07
    बाक
    -0.07
     Burkina
    -0.07
     ../../
    -0.07
     galaxy
    -0.07
     YAML
    -0.07
    POSITIVE LOGITS
     patents
    0.19
    Patent
    0.18
     inventions
    0.18
     patent
    0.17
     patented
    0.17
     invention
    0.16
     inventor
    0.15
     Patent
    0.15
     innovations
    0.13
     Innovations
    0.12
    Activations Density 0.026%

    No Known Activations