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. 54227
    Prev
    Next
    INDEX
    Explanations

    statement

    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
    Customize
    -0.08
     someday
    -0.07
     colon
    -0.07
     cust
    -0.07
     customer
    -0.07
    amt
    -0.07
     potatoes
    -0.07
    hof
    -0.07
     ICC
    -0.07
    }-${
    -0.07
    POSITIVE LOGITS
     పేర్క
    0.09
     náà
    0.08
     제대로
    0.08
    pción
    0.08
     correctly
    0.08
    listed
    0.08
    عال
    0.08
    sẹ
    0.08
    conditionally
    0.08
    .source
    0.08
    Activations Density 0.009%

    No Known Activations