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. 23134
    Prev
    Next
    INDEX
    Explanations

    violence and death

    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
    _settings
    -0.08
    久久
    -0.07
     dheer
    -0.07
     Watt
    -0.07
    Papa
    -0.07
    rare
    -0.07
    Settings
    -0.07
    極
    -0.07
    $type
    -0.07
     പുറത്തിറ
    -0.07
    POSITIVE LOGITS
     Perhaps
    0.08
     Linked
    0.08
     colegas
    0.08
     comrades
    0.08
     casualties
    0.08
     teng
    0.07
     cảnh
    0.07
    .Insert
    0.07
     چگونه
    0.07
    орию
    0.07
    Activations Density 0.042%

    No Known Activations