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. 119263
    Prev
    Next
    INDEX
    Explanations

    uses of objects

    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
    -0.09
    atorias
    -0.09
     refeições
    -0.08
    dat
    -0.08
     obrigação
    -0.07
     meat
    -0.07
    Η
    -0.07
    knowledge
    -0.07
     diets
    -0.07
    Subjects
    -0.07
    POSITIVE LOGITS
     quir
    0.08
    ิ่ง
    0.08
     Etsy
    0.08
    _ORDER
    0.08
     personals
    0.08
     ordine
    0.08
     Tal
    0.07
     browsing
    0.07
     Indy
    0.07
     그냥
    0.07
    Activations Density 0.208%

    No Known Activations