© 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. 3-RESID-POST-AA
    11. 13070
    Prev
    Next
    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fu
    -0.09
     μετα
    -0.09
     sɛ
    -0.09
     intervals
    -0.08
     منها
    -0.08
    是多少
    -0.08
     Fang
    -0.08
     definite
    -0.08
     hinge
    -0.08
    زيد
    -0.07
    POSITIVE LOGITS
    paper
    0.09
    Paper
    0.08
     reinvent
    0.07
    繁
    0.07
     Pink
    0.07
     Haw
    0.07
     Heer
    0.07
     jud
    0.07
     Vir
    0.07
     Paper
    0.07
    Activations Density 0.018%

    No Known Activations