© 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. 19-RESID-POST-AA
    11. 102684
    Prev
    Next
    INDEX
    Explanations

    Inventions and inventing

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     checkpoints
    -0.08
     engagements
    -0.08
     চলছে
    -0.08
     રહે
    -0.08
     থাকে
    -0.07
    есед
    -0.07
    202
    -0.07
    954
    -0.07
    Coverage
    -0.07
    越来越
    -0.07
    POSITIVE LOGITS
     invention
    0.29
     inventions
    0.26
     invented
    0.26
     founding
    0.24
     pioneering
    0.24
     invent
    0.22
     inventor
    0.21
     pioneered
    0.21
     groundbreaking
    0.21
     pioneers
    0.21
    Activations Density 0.141%

    No Known Activations