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. 15-RESID-POST-AA
    6. 19302
    Prev
    Next
    INDEX
    Explanations

    playful

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرکزی
    -0.09
     centrale
    -0.09
     المركزي
    -0.09
    _UClass
    -0.09
     malheureusement
    -0.09
     కేంద్ర
    -0.09
     məl
    -0.09
     المركز
    -0.08
     unforeseen
    -0.08
    Wohn
    -0.08
    POSITIVE LOGITS
     teasing
    0.14
     playful
    0.14
     rivalry
    0.12
    互动
    0.11
     conspir
    0.10
     flirt
    0.10
     joking
    0.10
     spirited
    0.10
     tease
    0.10
     bargaining
    0.09
    Activations Density 0.015%

    No Known Activations