© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48036
    Prev
    Next
    INDEX
    Explanations

    html markdown

    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
    rafts
    -0.08
     لكنها
    -0.08
    惯
    -0.08
    )&&
    -0.08
     Parmesan
    -0.07
     وتأ
    -0.07
    guns
    -0.07
    TASK
    -0.07
    tert
    -0.07
     funcionário
    -0.07
    POSITIVE LOGITS
    联系方式
    0.15
    网址
    0.14
    联系电话
    0.13
     hotline
    0.12
     kontakt
    0.12
    官方网站
    0.12
     સંપર્ક
    0.12
     www
    0.12
     contacter
    0.12
    官方网址
    0.12
    Activations Density 0.038%

    No Known Activations