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

    Neuronpedia

    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. 47423
    Prev
    Next
    INDEX
    Explanations

    legal and international affairs

    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
     girlfriend
    -0.11
     Terraria
    -0.10
     Maine
    -0.10
     Rancho
    -0.10
     Johnny
    -0.10
     horsepower
    -0.09
     cider
    -0.09
     candy
    -0.09
     cellar
    -0.09
     blueberry
    -0.09
    POSITIVE LOGITS
     UNESCO
    0.19
     UNICEF
    0.16
     الأمم
    0.15
     ASEAN
    0.15
     treaty
    0.14
     국제
    0.14
     আন্তর্জাতিক
    0.14
    “一带一路
    0.14
     WTO
    0.14
     humanitarian
    0.13
    Activations Density 0.164%

    No Known Activations