© 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. 64004
    Prev
    Next
    INDEX
    Explanations

    hardware components

    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
     patient's
    -0.08
     客
    -0.08
     societal
    -0.08
     opponent
    -0.08
     exile
    -0.08
     Entertainment
    -0.08
     مری
    -0.07
     emociones
    -0.07
     taobh
    -0.07
     留
    -0.07
    POSITIVE LOGITS
     connectors
    0.09
    匹
    0.09
    arette
    0.09
     ম্যাচ
    0.08
     screws
    0.08
     réunion
    0.08
     foam
    0.08
     réunions
    0.08
     MATCH
    0.08
    采购
    0.08
    Activations Density 0.095%

    No Known Activations