© 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. 11-RESID-POST-AA
    11. 45342
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تجربة
    -0.08
     lese
    -0.08
     Grind
    -0.08
     reins
    -0.08
     Soll
    -0.08
     xmlhttp
    -0.07
     mids
    -0.07
    ावट
    -0.07
     trunk
    -0.07
     ^^
    -0.07
    POSITIVE LOGITS
    ûn
    0.08
     Johnson
    0.08
     sellers
    0.08
     authors
    0.08
     بتوان
    0.08
     adults
    0.07
     CF
    0.07
    0.07
    Dont
    0.07
    赵
    0.07
    Activations Density 0.076%
    No Known Activations