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. 15-RESID-POST-AA
    6. 19554
    Prev
    Next
    INDEX
    Explanations

    ’re

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     गर्दा
    -0.10
    网页登录
    -0.09
    .readline
    -0.09
    riaman
    -0.09
    rlə
    -0.09
    ireo
    -0.09
     Ար
    -0.09
    相关阅读
    -0.09
    irimbo
    -0.09
    riamanitra
    -0.09
    POSITIVE LOGITS
     professional
    0.08
    ais
    0.08
     avons
    0.08
     professions
    0.08
     careers
    0.08
     powerful
    0.08
    0.08
     છીએ
    0.08
     здесь
    0.08
     interconnected
    0.08
    Activations Density 0.013%

    No Known Activations