© 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. 78377
    Prev
    Next
    INDEX
    Explanations

    Platinum

    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
    Derived
    -0.08
     derived
    -0.08
    argent
    -0.08
     glare
    -0.08
    섭
    -0.08
     Derived
    -0.08
    》中
    -0.07
    MLElement
    -0.07
     laquelle
    -0.07
    ס
    -0.07
    POSITIVE LOGITS
    ッグ
    0.09
    _xyz
    0.08
     DAG
    0.08
    -tail
    0.08
    島
    0.08
    �
    0.07
    dyr
    0.07
    集团
    0.07
     islands
    0.07
     acetate
    0.07
    Activations Density 0.002%

    No Known Activations