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. 103024
    Prev
    Next
    INDEX
    Explanations

    Disk cleanup instructions

    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
    授
    -0.07
    Route
    -0.07
     salient
    -0.07
    DES
    -0.07
    纲
    -0.07
     zainteres
    -0.07
    _sk
    -0.07
    ільш
    -0.07
    १
    -0.07
    цип
    -0.07
    POSITIVE LOGITS
     تنظيف
    0.13
     删除
    0.11
     nettoyage
    0.11
     limpeza
    0.11
     déchets
    0.11
     cleaning
    0.11
     التخلص
    0.11
    垃圾
    0.10
     Cleaning
    0.10
     limpieza
    0.10
    Activations Density 0.012%

    No Known Activations