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. 77530
    Prev
    Next
    INDEX
    Explanations

    math sequences

    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
    793
    -0.08
    ache
    -0.08
    464
    -0.07
    light
    -0.07
    HTTPS
    -0.07
    磨
    -0.07
     tuned
    -0.07
    resh
    -0.07
    ühl
    -0.07
    794
    -0.07
    POSITIVE LOGITS
    累计
    0.15
     cumulative
    0.13
     acumul
    0.13
    umulative
    0.13
    累
    0.12
     Sum
    0.12
     accumulation
    0.11
     sum
    0.11
     sums
    0.11
     accumulate
    0.11
    Activations Density 0.049%

    No Known Activations