© 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. 75455
    Prev
    Next
    INDEX
    Explanations

    tab

    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
    倾
    -0.08
     anime
    -0.07
     intuition
    -0.07
    go
    -0.07
     carácter
    -0.07
     caractère
    -0.07
     mirac
    -0.07
     excerpt
    -0.07
    unnels
    -0.07
    ක්ෂ
    -0.07
    POSITIVE LOGITS
    /window
    0.10
     reng
    0.10
    Beacon
    0.08
    /context
    0.08
     ehd
    0.08
     clogged
    0.08
     bancaria
    0.08
    Marketplace
    0.08
    acado
    0.08
     dédiée
    0.08
    Activations Density 0.004%

    No Known Activations