© 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. 30864
    Prev
    Next
    INDEX
    Explanations

    markdown formatting characters

    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
    ाधिक
    -0.08
    Invalidate
    -0.07
    -o
    -0.07
    ocratic
    -0.07
    ुक
    -0.07
    дад
    -0.07
    ापन
    -0.07
    bre
    -0.07
     Есть
    -0.07
    ುಕ್ತ
    -0.07
    POSITIVE LOGITS
     aka
    0.11
     hingegen
    0.08
    .promise
    0.08
     dire
    0.08
     Agro
    0.07
     Bluff
    0.07
    etty
    0.07
     naman
    0.07
     అనే
    0.07
     formerly
    0.07
    Activations Density 0.062%

    No Known Activations