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. 88155
    Prev
    Next
    INDEX
    Explanations

    Math

    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
    그
    -0.08
    paces
    -0.08
    Sketch
    -0.08
     streamlined
    -0.08
    ingtone
    -0.07
     Viz
    -0.07
     organism
    -0.07
    attention
    -0.07
    Outstanding
    -0.07
    (annotation
    -0.07
    POSITIVE LOGITS
    .ceil
    0.09
    .Abs
    0.08
    陰
    0.08
    othermal
    0.08
    .floor
    0.08
    759
    0.08
     porn
    0.08
     calculated
    0.07
     interm
    0.07
    .sqrt
    0.07
    Activations Density 0.002%

    No Known Activations