© 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. 50650
    Prev
    Next
    INDEX
    Explanations

    skills and learning

    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
    期开奖
    -0.08
     élu
    -0.08
    期开奖结果
    -0.08
     eleito
    -0.07
    ^)
    -0.07
     erre
    -0.07
     bulundu
    -0.07
     заявления
    -0.07
    וצאות
    -0.07
    bean
    -0.07
    POSITIVE LOGITS
     كيفية
    0.18
     skills
    0.16
     vaardigheden
    0.16
     навы
    0.16
     about
    0.15
     tentang
    0.15
     tungkol
    0.15
     lessons
    0.15
    技能
    0.15
     درباره
    0.14
    Activations Density 0.127%

    No Known Activations