© 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. 110249
    Prev
    Next
    INDEX
    Explanations

    Character fusion/traits

    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
     관계
    -0.07
     layanan
    -0.07
     onderhouden
    -0.07
    Под
    -0.07
    违反
    -0.07
    Gratis
    -0.07
    等
    -0.07
    ormon
    -0.07
    ataj
    -0.07
    相关文章
    -0.07
    POSITIVE LOGITS
     merged
    0.12
     blended
    0.11
    -inspired
    0.10
     merge
    0.10
    combined
    0.10
     kombiniert
    0.10
    combine
    0.10
    Merged
    0.10
    merge
    0.10
     combined
    0.10
    Activations Density 0.025%

    No Known Activations