Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23692
    Prev
    Next
    INDEX
    Explanations

    of

    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
     видно
    -0.08
    starz
    -0.08
     thanks
    -0.08
     ம
    -0.07
     VS
    -0.07
     можуть
    -0.07
     CIS
    -0.07
    •
    -0.07
    VS
    -0.07
    arette
    -0.07
    POSITIVE LOGITS
    办法
    0.08
    拜
    0.08
     revel
    0.08
    ffs
    0.08
     extr
    0.07
    apis
    0.07
    振
    0.07
     Hunts
    0.07
     Fully
    0.07
     ze
    0.07
    Activations Density 0.009%

    No Known Activations