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. 112445
    Prev
    Next
    INDEX
    Explanations

    fluid

    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
    ottest
    -0.08
    vide
    -0.08
    column
    -0.07
     substring
    -0.07
    embr
    -0.07
    postal
    -0.07
    nacht
    -0.07
    职位
    -0.07
    在哪里
    -0.07
    inguished
    -0.07
    POSITIVE LOGITS
     liters
    0.10
    .buffer
    0.09
    0.08
     flush
    0.08
     supplementation
    0.08
     तेजी
    0.08
     компен
    0.08
    ทัน
    0.08
     fluid
    0.08
     hızlı
    0.08
    Activations Density 0.003%

    No Known Activations