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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75994
    Prev
    Next
    INDEX
    Explanations

    opposite

    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
     č
    -0.09
     GHz
    -0.08
     تور
    -0.08
     Vogue
    -0.08
     props
    -0.07
     Told
    -0.07
     Claire
    -0.07
     柳
    -0.07
     Ricky
    -0.07
     shaved
    -0.07
    POSITIVE LOGITS
     oppos
    0.11
     negativo
    0.10
     negatif
    0.10
     отриц
    0.10
     negat
    0.09
     negatives
    0.09
    .neg
    0.09
     negativos
    0.09
    Negative
    0.08
     Negative
    0.08
    Activations Density 0.008%

    No Known Activations