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. 113946
    Prev
    Next
    INDEX
    Explanations

    I

    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
    -fashion
    -0.09
     pão
    -0.08
     filings
    -0.08
     vuel
    -0.08
     dum
    -0.08
    还是
    -0.08
    ането
    -0.08
    相关文章
    -0.08
     vín
    -0.07
     azúcar
    -0.07
    POSITIVE LOGITS
    исты
    0.08
    arrage
    0.07
    Qu
    0.07
    شت
    0.07
     Qu
    0.07
     re
    0.07
     حکم
    0.07
    $l
    0.07
     
    0.07
    Study
    0.07
    Activations Density 0.033%

    No Known Activations