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. 113031
    Prev
    Next
    INDEX
    Explanations

    French

    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
     doe
    -0.09
     fortune
    -0.08
     mum
    -0.08
     canto
    -0.07
    abd
    -0.07
     odo
    -0.07
     probable
    -0.07
     lentes
    -0.07
     naive
    -0.07
    ိုင်
    -0.07
    POSITIVE LOGITS
     erupted
    0.08
     зак
    0.08
     ব্য
    0.08
    fé
    0.07
     పన
    0.07
     bestellt
    0.07
    ప్ర
    0.07
     WLAN
    0.07
    క్క
    0.07
     sé
    0.07
    Activations Density 0.065%

    No Known Activations