© 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. 78378
    Prev
    Next
    INDEX
    Explanations

    AI agent communication

    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
    prediction
    -0.09
     prediction
    -0.08
    erap
    -0.08
    fog
    -0.08
    uli
    -0.08
     financing
    -0.08
    pow
    -0.08
    aur
    -0.08
     blu
    -0.08
    _prediction
    -0.08
    POSITIVE LOGITS
    .",↵
    0.08
     Lidl
    0.08
     করেছি
    0.08
     Diy
    0.08
    予定
    0.08
     Kandid
    0.08
    .",
    0.08
    。”↵
    0.08
     продолжа
    0.08
     Lotto
    0.08
    Activations Density 0.000%

    No Known Activations