© 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. 102866
    Prev
    Next
    INDEX
    Explanations

    Meta

    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
     tweeting
    -0.09
     stationery
    -0.09
    etakse
    -0.08
    ării
    -0.08
    endor
    -0.08
     behavior
    -0.08
     appreciation
    -0.08
    FEATURE
    -0.08
     人気
    -0.08
     celebration
    -0.08
    POSITIVE LOGITS
     Platforms
    0.10
     Industries
    0.09
     byose
    0.09
     platforms
    0.09
     Systems
    0.09
     AI
    0.08
     HPC
    0.08
    Ports
    0.08
    .Debug
    0.07
     Archives
    0.07
    Activations Density 0.003%

    No Known Activations