© 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. 7-RESID-POST-AA
    11. 1458
    Prev
    Next
    INDEX
    Explanations

    lifespan/longevity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fan
    -0.08
     owner
    -0.08
     knob
    -0.08
     बैठक
    -0.08
     propietario
    -0.07
     dầu
    -0.07
     essentielle
    -0.07
    (del
    -0.07
     के
    -0.07
     तेल
    -0.07
    POSITIVE LOGITS
     lifespan
    0.14
     longevity
    0.12
     expectancy
    0.11
     mortality
    0.11
    寿
    0.11
     মৃত্য
    0.10
     मृत्यु
    0.10
    Deaths
    0.10
     obituary
    0.10
    Span
    0.09
    Activations Density 0.031%

    No Known Activations