© 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. 23-RESID-POST-AA
    11. 96636
    Prev
    Next
    INDEX
    Explanations

    Chinese manufacturing processes

    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
    ندی
    -0.08
    ized
    -0.08
     medi
    -0.08
     flattened
    -0.07
    oji
    -0.07
     Neuro
    -0.07
     diversified
    -0.07
     squander
    -0.07
    inizi
    -0.07
    aji
    -0.07
    POSITIVE LOGITS
    罩
    0.09
    刻
    0.09
     أق
    0.08
    kker
    0.08
    绑定
    0.07
     arreglo
    0.07
    等
    0.07
    .xt
    0.07
     그림
    0.07
    	X
    0.07
    Activations Density 0.001%

    No Known Activations