© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 112413
    Prev
    Next
    INDEX
    Explanations

    preferred terminology

    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
     contexts
    -0.07
    }↵↵//
    -0.07
    分享
    -0.07
    �
    -0.07
    _DUP
    -0.07
    ↵
    -0.07
    ु
    -0.07
     context
    -0.07
    _CONTEXT
    -0.07
    实现
    -0.07
    POSITIVE LOGITS
     вместо
    0.13
     nomen
    0.12
     statt
    0.12
     istället
    0.11
     instead
    0.11
    mere
    0.10
    Instead
    0.10
     terminology
    0.10
     zami
    0.10
    instead
    0.09
    Activations Density 0.081%

    No Known Activations