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. 60690
    Prev
    Next
    INDEX
    Explanations

    object

    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
     BRAND
    -0.07
     ق
    -0.07
     PLAYER
    -0.07
    čina
    -0.07
     détermin
    -0.07
     Won
    -0.07
    urst
    -0.07
     活
    -0.07
    Kana
    -0.07
     nét
    -0.07
    POSITIVE LOGITS
     기반
    0.08
     ents
    0.08
     mı
    0.08
     IO
    0.08
     dementia
    0.08
    ordnet
    0.08
     ориент
    0.07
     tractors
    0.07
     ಬೆ
    0.07
     begyn
    0.07
    Activations Density 0.002%

    No Known Activations