© 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. 43547
    Prev
    Next
    INDEX
    Explanations

    Prompt/Article Beginnings

    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
    ’avant
    -0.08
     irm
    -0.08
     весьма
    -0.08
     discourse
    -0.08
    ’avenir
    -0.08
    进去
    -0.08
    随后
    -0.08
     consist
    -0.08
     આપવામાં
    -0.08
    ouvre
    -0.07
    POSITIVE LOGITS
     хотите
    0.15
     ترغب
    0.13
     vuoi
    0.13
     quieres
    0.13
     želite
    0.12
     souhaitez
    0.12
     möchtest
    0.12
     szeret
    0.11
     chcete
    0.11
     تريد
    0.11
    Activations Density 0.216%

    No Known Activations