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. 49723
    Prev
    Next
    INDEX
    Explanations

    ordered lists

    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
    282
    -0.09
     מדובר
    -0.08
    -0.08
    080
    -0.07
    大道
    -0.07
    一次
    -0.07
    -0.07
    631
    -0.07
    ായിരുന്നു
    -0.07
     blowing
    -0.07
    POSITIVE LOGITS
     elkaar
    0.10
     ним
    0.10
    ucia
    0.09
     nhau
    0.09
     siebie
    0.09
     Theo
    0.08
     Lak
    0.08
     пользователя
    0.08
     niego
    0.08
    Kyle
    0.08
    Activations Density 0.182%

    No Known Activations