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. 111848
    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
     Volunteers
    -0.09
     Voltage
    -0.09
     Volt
    -0.08
    Voltage
    -0.08
    Ju
    -0.08
     Enlight
    -0.08
    Volt
    -0.08
    حب
    -0.08
    volt
    -0.08
     Illumin
    -0.08
    POSITIVE LOGITS
     DG
    0.09
    Shuffle
    0.08
     सीट
    0.08
    .shuffle
    0.07
     shp
    0.07
     brakes
    0.07
     garment
    0.07
     shuffle
    0.07
     flotte
    0.07
    ਮੀ
    0.07
    Activations Density 0.000%

    No Known Activations