© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47929
    Prev
    Next
    INDEX
    Explanations

    say "background"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ণে
    -0.07
    -0.07
    ישה
    -0.07
    -0.07
    íncipe
    -0.07
    .Ordinal
    -0.07
    817
    -0.07
     الإنسان
    -0.06
     ịdị
    -0.06
     koers
    -0.06
    POSITIVE LOGITS
     background
    0.75
    背景
    0.71
    Background
    0.69
     Background
    0.69
    background
    0.68
    _background
    0.67
     achtergrond
    0.67
    	background
    0.65
    .background
    0.65
     Hintergrund
    0.64
    Activations Density 0.230%

    No Known Activations