© 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. 70770
    Prev
    Next
    INDEX
    Explanations

    draw

    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
     həyat
    -0.09
     hesap
    -0.08
     ktorý
    -0.08
     çöz
    -0.07
     хран
    -0.07
     ed
    -0.07
     পাশে
    -0.07
     stejně
    -0.07
     삶
    -0.07
     côté
    -0.07
    POSITIVE LOGITS
    人数
    0.09
    quad
    0.09
     количество
    0.08
    Args
    0.08
     defended
    0.08
     defend
    0.08
     quad
    0.08
     количества
    0.08
     произвед
    0.08
    发动
    0.08
    Activations Density 0.004%

    No Known Activations