© 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 EvalsExportsinterp-engineNEWAPI 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. 71184
    Prev
    Next
    INDEX
    Explanations

    partition protocol

    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
     Leh
    -0.08
    �
    -0.08
     geb
    -0.08
    诊
    -0.07
    ，还
    -0.07
     bên
    -0.07
     poisoning
    -0.07
    ु
    -0.07
     blessing
    -0.07
     Conditioning
    -0.07
    POSITIVE LOGITS
    Din
    0.08
    (net
    0.08
    Neither
    0.08
     �
    0.07
    ovaných
    0.07
     결국
    0.07
    Greater
    0.07
    denes
    0.07
     좌
    0.07
    numer
    0.07
    Activations Density 0.000%

    No Known Activations