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. 65181
    Prev
    Next
    INDEX
    Explanations

    Interface/Trainer/Pipeline

    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
    unate
    -0.09
     punct
    -0.09
     Warren
    -0.08
     Herm
    -0.08
     câ
    -0.07
     hav
    -0.07
     HAV
    -0.07
     unread
    -0.07
     proč
    -0.07
     rename
    -0.07
    POSITIVE LOGITS
    Contato
    0.08
    .routing
    0.08
    .auto
    0.08
     הא
    0.08
     высокого
    0.08
    Algo
    0.08
     itin
    0.07
    латы
    0.07
     Algo
    0.07
     Construction
    0.07
    Activations Density 0.005%

    No Known Activations