© 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. 44850
    Prev
    Next
    INDEX
    Explanations

    from

    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
    units
    -0.08
    -meter
    -0.07
    äfte
    -0.07
    ūs
    -0.07
    serde
    -0.07
    zial
    -0.07
    ্ভ
    -0.07
     Martech
    -0.07
     meter
    -0.07
     litigation
    -0.07
    POSITIVE LOGITS
    _MED
    0.09
     الأولى
    0.08
     MED
    0.08
     ''){↵
    0.08
     아니라
    0.08
     CHECK
    0.08
     прошлого
    0.08
     hout
    0.07
    Ign
    0.07
     također
    0.07
    Activations Density 0.010%

    No Known Activations