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. 58728
    Prev
    Next
    INDEX
    Explanations

    Flowers

    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
     daban
    -0.08
     요
    -0.08
     tighten
    -0.07
     pommes
    -0.07
     ות
    -0.07
    /problems
    -0.07
     cabinetry
    -0.07
     phụ
    -0.07
    bian
    -0.07
     নম
    -0.07
    POSITIVE LOGITS
     overwhelming
    0.13
     густ
    0.11
     snowfall
    0.11
     overwhelmed
    0.11
     Sprinkle
    0.11
     Shower
    0.11
     dazz
    0.11
     overwhelm
    0.11
     foliage
    0.10
     overwhel
    0.10
    Activations Density 0.090%

    No Known Activations