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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69719
    Prev
    Next
    INDEX
    Explanations

    first-person narrative

    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
     invariant
    -0.08
    Invariant
    -0.08
    面积
    -0.07
    同期
    -0.07
     seedlings
    -0.07
    家
    -0.07
     học
    -0.07
    家的
    -0.07
    固
    -0.07
    ����
    -0.07
    POSITIVE LOGITS
     причем
    0.08
     ואני
    0.08
    (em
    0.08
    /xml
    0.08
    _rules
    0.08
     pretending
    0.08
    bies
    0.08
    Rules
    0.08
     Undert
    0.08
     tasked
    0.08
    Activations Density 0.007%

    No Known Activations