Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111985
    Prev
    Next
    INDEX
    Explanations

    Amazon

    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
     soddis
    -0.09
     Coco
    -0.08
    منٹ
    -0.08
    طلب
    -0.08
     свер
    -0.08
     Directors
    -0.08
     완료
    -0.08
     efekt
    -0.08
    .power
    -0.08
    Mortgage
    -0.07
    POSITIVE LOGITS
     rainforest
    0.09
     semana
    0.08
     Arctic
    0.08
     jungle
    0.08
     jung
    0.08
     flora
    0.08
    菌
    0.07
    �
    0.07
     canoe
    0.07
     avenue
    0.07
    Activations Density 0.003%

    No Known Activations