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. 49403
    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
     locom
    -0.09
    jaz
    -0.08
    Global
    -0.07
     frequ
    -0.07
    _HDR
    -0.07
     Laz
    -0.07
     병
    -0.07
    )="
    -0.07
     местах
    -0.07
     mold
    -0.07
    POSITIVE LOGITS
    数学
    0.09
    /math
    0.08
     principle
    0.08
    Arithmetic
    0.08
     اصل
    0.08
     arithmetic
    0.08
     garden
    0.08
    iday
    0.08
     আপ
    0.08
    akus
    0.08
    Activations Density 0.008%

    No Known Activations