© 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. 129315
    Prev
    Next
    INDEX
    Explanations

    defense

    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
    737
    -0.08
    veno
    -0.08
     මහ
    -0.07
    .ico
    -0.07
     Stat
    -0.07
    බ
    -0.07
    起来
    -0.07
    .zaxxer
    -0.07
    Analy
    -0.07
     Zuh
    -0.07
    POSITIVE LOGITS
     protection
    0.11
     रक्षा
    0.11
     camouflage
    0.11
     defense
    0.11
     deterr
    0.10
    Protection
    0.10
    保护
    0.10
     защиты
    0.10
     defensa
    0.10
     defend
    0.10
    Activations Density 0.009%

    No Known Activations