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. 9223
    Prev
    Next
    INDEX
    Explanations

    finding, using

    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
    ÇA
    -0.08
    ça
    -0.08
     kamen
    -0.07
    вар
    -0.07
     poderão
    -0.07
    rió
    -0.07
    �್
    -0.07
    Smart
    -0.07
    ße
    -0.07
     pourrez
    -0.07
    POSITIVE LOGITS
     آسان
    0.09
    来说
    0.08
    容易
    0.08
     lastig
    0.08
     pronounce
    0.08
    有限
    0.08
    起来
    0.08
    而言
    0.08
     어렵
    0.08
     પડે
    0.07
    Activations Density 0.100%

    No Known Activations