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. 119262
    Prev
    Next
    INDEX
    Explanations

    Consular affairs

    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
    shaus
    -0.08
    หัว
    -0.08
     छल
    -0.08
     chord
    -0.08
     temporal
    -0.08
     opet
    -0.07
     cauliflower
    -0.07
    onga
    -0.07
    eer
    -0.07
     regenerative
    -0.07
    POSITIVE LOGITS
     protects
    0.11
     humanitarian
    0.11
     Protect
    0.10
    保护
    0.10
    Protect
    0.10
    Protection
    0.10
     보호
    0.10
     protecting
    0.09
     kidnapped
    0.09
     protective
    0.09
    Activations Density 0.033%

    No Known Activations