© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26576
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     optimisation
    -0.09
     stress
    -0.08
    Discussion
    -0.08
     discussions
    -0.08
    Stress
    -0.08
    ательный
    -0.08
     Discussion
    -0.07
    ોફ
    -0.07
    stress
    -0.07
    Conference
    -0.07
    POSITIVE LOGITS
     earning
    0.08
     Kalk
    0.08
     Plenty
    0.08
     Renting
    0.08
     सिं
    0.08
     expectancy
    0.08
     Bub
    0.07
    cendo
    0.07
     glam
    0.07
     sank
    0.07
    Activations Density 0.001%

    No Known Activations