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. 52817
    Prev
    Next
    INDEX
    Explanations

    out

    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
     stamp
    -0.07
    料
    -0.07
     Steel
    -0.07
     steel
    -0.07
     herald
    -0.07
     ca
    -0.07
    卷
    -0.07
    男性
    -0.07
     breach
    -0.07
    护理
    -0.07
    POSITIVE LOGITS
    count
    0.09
     controllo
    0.08
     controlar
    0.08
    degree
    0.08
     compter
    0.08
    .count
    0.08
    jumlah
    0.08
     नियंत्रण
    0.08
     контроля
    0.08
    ocabulary
    0.08
    Activations Density 0.002%

    No Known Activations