© 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 EvalsExportsinterp-engineNEWAPI 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. 111368
    Prev
    Next
    INDEX
    Explanations

    Feynman Method

    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
    vd
    -0.08
    ubes
    -0.07
    sqrt
    -0.07
    fluid
    -0.07
    excluding
    -0.07
    вет
    -0.07
     Rays
    -0.07
     acknowledges
    -0.07
     acknowledge
    -0.07
     suplementos
    -0.07
    POSITIVE LOGITS
     Persona
    0.09
     õpet
    0.09
     Técnica
    0.09
     Teach
    0.09
    เด็ก
    0.09
     Teaching
    0.08
     শেখ
    0.08
    নীতি
    0.08
     শিশু
    0.08
     শিক্ষক
    0.08
    Activations Density 0.001%

    No Known Activations