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. 78134
    Prev
    Next
    INDEX
    Explanations

    government and law

    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
     Spa
    -0.08
    spa
    -0.08
     makeover
    -0.08
     actress
    -0.08
    UDA
    -0.07
     Actress
    -0.07
    .selenium
    -0.07
     actresses
    -0.07
     spa
    -0.07
     Docker
    -0.07
    POSITIVE LOGITS
    否则
    0.09
     tendencies
    0.09
     corruption
    0.09
     भ्रष्ट
    0.08
    Prevent
    0.08
     vigilance
    0.08
    _WARNING
    0.08
     tendency
    0.08
     Prevent
    0.08
     vigilant
    0.08
    Activations Density 0.005%

    No Known Activations