© 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. 23-RESID-POST-AA
    11. 50873
    Prev
    Next
    INDEX
    Explanations

    Mao Zedong or Xi Jinping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apik
    -0.09
     taş
    -0.09
     muestra
    -0.08
    اپ
    -0.08
    ándolo
    -0.08
     শুক
    -0.08
    oule
    -0.08
     mostró
    -0.08
     تبد
    -0.08
    �োগ
    -0.07
    POSITIVE LOGITS
    讲
    0.09
     речи
    0.09
    演
    0.09
     speeches
    0.09
    講
    0.08
     설
    0.08
    :w
    0.08
    选
    0.08
     संवाद
    0.08
     बातचीत
    0.08
    Activations Density 0.002%

    No Known Activations