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. 12845
    Prev
    Next
    INDEX
    Explanations

    bit packing

    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
     shock
    -0.09
     shocked
    -0.09
    shock
    -0.08
     رد
    -0.08
    Shock
    -0.08
     prices
    -0.08
    加盟
    -0.08
     fiyat
    -0.07
     AMP
    -0.07
    价格
    -0.07
    POSITIVE LOGITS
    .Bit
    0.10
    .bit
    0.09
    .COLUMN
    0.09
    Quart
    0.08
     bit
    0.08
     Ми
    0.08
    ంలోని
    0.08
    (bits
    0.08
     बिट
    0.08
     dimainkan
    0.08
    Activations Density 0.004%

    No Known Activations