© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 103270
    Prev
    Next
    INDEX
    Explanations

    instruction manual

    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
     թվականին
    -0.09
     roedd
    -0.09
     gurluş
    -0.09
    -nyň
    -0.08
    არეობ
    -0.08
     ամբողջ
    -0.08
     unglaublich
    -0.08
     nassi
    -0.08
    -ամ
    -0.08
     Berdimuhamed
    -0.08
    POSITIVE LOGITS
    /provider
    0.09
    /topic
    0.08
    /test
    0.08
    /product
    0.08
     โดย
    0.08
    .argv
    0.08
    /testify
    0.08
    icz
    0.08
    .q
    0.08
    /support
    0.08
    Activations Density 0.000%

    No Known Activations