© 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. 91380
    Prev
    Next
    INDEX
    Explanations

    رو

    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
     Negra
    -0.08
     Schluss
    -0.08
     trava
    -0.08
    ასრულ
    -0.08
     Saddle
    -0.08
     Woods
    -0.08
     Cream
    -0.08
     Colonial
    -0.08
    purple
    -0.08
    imited
    -0.08
    POSITIVE LOGITS
    -scale
    0.08
    Transaction
    0.08
     expiry
    0.07
     body
    0.07
    UMENT
    0.07
    body
    0.07
    ocytes
    0.07
    336
    0.07
    त्त्व
    0.07
     vasos
    0.07
    Activations Density 0.003%

    No Known Activations