© 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. 129402
    Prev
    Next
    INDEX
    Explanations

    arithmetic problems

    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
     �
    -0.08
     سير
    -0.08
     graft
    -0.07
    урнал
    -0.07
     مز
    -0.07
     curated
    -0.07
     ہونا
    -0.07
     قوية
    -0.07
    ，以及
    -0.07
     دعا
    -0.07
    POSITIVE LOGITS
    displaystyle
    0.08
    €
    0.08
    _pts
    0.08
     Matem
    0.08
    units
    0.08
    geom
    0.07
     ammon
    0.07
    ume
    0.07
    数学
    0.07
     Analyst
    0.07
    Activations Density 0.017%

    No Known Activations