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. 112898
    Prev
    Next
    INDEX
    Explanations

    square root

    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
     의료
    -0.08
     �
    -0.08
    ofilm
    -0.08
     지속
    -0.08
    Houston
    -0.08
     svě
    -0.08
    -lasting
    -0.08
    تنا
    -0.08
     어떻게
    -0.08
     تهران
    -0.08
    POSITIVE LOGITS
     Decimal
    0.09
     rounding
    0.08
    .Sqrt
    0.08
    qrt
    0.08
    Arithmetic
    0.08
     राशि
    0.08
     decimal
    0.08
     Arithmetic
    0.08
     harmonic
    0.08
     irrational
    0.08
    Activations Density 0.006%

    No Known Activations