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. 106198
    Prev
    Next
    INDEX
    Explanations

    stake

    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
     seules
    -0.08
     convection
    -0.07
     seuls
    -0.07
    ç
    -0.07
     piace
    -0.07
     guys
    -0.07
     Pops
    -0.07
    essa
    -0.07
    一下
    -0.07
     draa
    -0.07
    POSITIVE LOGITS
    isini
    0.09
     हिस्सा
    0.08
     fisheries
    0.08
     holdings
    0.08
     yaptı
    0.08
     Portland
    0.08
     가져
    0.07
     Liga
    0.07
     Kashmir
    0.07
     infringement
    0.07
    Activations Density 0.015%

    No Known Activations