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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43748
    Prev
    Next
    INDEX
    Explanations

    specifically

    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
     ante
    -0.09
    тен
    -0.08
     außerdem
    -0.08
    ępu
    -0.08
    ուհ
    -0.08
     sannan
    -0.08
     выполня
    -0.08
     иногда
    -0.08
     inoltre
    -0.08
    יכים
    -0.08
    POSITIVE LOGITS
     focusing
    0.09
    的是
    0.07
     tracking
    0.07
     probing
    0.07
    auen
    0.07
     especificamente
    0.07
     assessing
    0.07
    Cr
    0.07
     -->
    0.07
     lust
    0.07
    Activations Density 0.064%

    No Known Activations