Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78585
    Prev
    Next
    INDEX
    Explanations

    lying

    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
     wrist
    -0.09
    grö
    -0.08
     Wrist
    -0.08
    chanical
    -0.08
     effortless
    -0.08
     comfortable
    -0.08
    ২৬
    -0.08
    آپ
    -0.07
     mẫu
    -0.07
    .Depth
    -0.07
    POSITIVE LOGITS
    启
    0.08
     perig
    0.08
     विप
    0.08
     激
    0.07
     reacting
    0.07
     ##↵
    0.07
    )#
    0.07
     NSArray
    0.07
     NSString
    0.07
    Us
    0.07
    Activations Density 0.002%

    No Known Activations