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. 90079
    Prev
    Next
    INDEX
    Explanations

    mongol empire

    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
     Explained
    -0.09
     �
    -0.09
    бран
    -0.09
    .board
    -0.09
    ж
    -0.09
    .enqueue
    -0.08
     強
    -0.08
     强
    -0.08
    єї
    -0.08
    AKA
    -0.08
    POSITIVE LOGITS
     sentimientos
    0.09
     per
    0.08
     sem
    0.07
     sentimiento
    0.07
     triangle
    0.07
     context
    0.07
     sentimentos
    0.07
     आ
    0.07
     Kreuz
    0.06
     '
    0.06
    Activations Density 0.000%

    No Known Activations