Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 119312
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    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
     GI
    -0.08
     එක
    -0.08
    cron
    -0.08
    folder
    -0.08
     aliment
    -0.07
     TMP
    -0.07
     cov
    -0.07
    cov
    -0.07
    jobs
    -0.07
     التخ
    -0.07
    POSITIVE LOGITS
     यांच्या
    0.10
     Zhang
    0.10
     رضي
    0.10
     यांनी
    0.09
     张
    0.09
    先生
    0.09
     himself
    0.08
     ibn
    0.08
     씨
    0.08
     Zhu
    0.08
    Activations Density 0.014%

    No Known Activations