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. 53029
    Prev
    Next
    INDEX
    Explanations

    One

    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
     eest
    -0.08
     But
    -0.08
     જોકે
    -0.07
    ім
    -0.07
     арен
    -0.07
     yük
    -0.07
     load
    -0.07
    ensitive
    -0.07
    -0.07
     ანგარიშ
    -0.07
    POSITIVE LOGITS
    ुलाई
    0.07
    aggi
    0.07
    Aug
    0.07
     perpet
    0.07
    177
    0.07
    \">↵
    0.07
     déficit
    0.07
    ithe
    0.07
    �
    0.07
    978
    0.07
    Activations Density 0.004%

    No Known Activations