© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54783
    Prev
    Next
    INDEX
    Explanations

    Regional/geopolitical issues

    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
     هاتف
    -0.09
    Producto
    -0.08
     الهاتف
    -0.08
     कर्मचारी
    -0.08
    hto
    -0.07
     scolaire
    -0.07
    .Program
    -0.07
     العمر
    -0.07
    stånd
    -0.07
    oro
    -0.07
    POSITIVE LOGITS
     destabil
    0.09
    荡
    0.09
     negotiations
    0.09
     politics
    0.08
     politik
    0.08
     stakeholders
    0.08
    Negoti
    0.08
     politischen
    0.08
     instability
    0.08
    领域
    0.08
    Activations Density 0.019%

    No Known Activations