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. 78579
    Prev
    Next
    INDEX
    Explanations

    Asking "what is called"

    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
     Mehr
    -0.07
     Res
    -0.07
    יה
    -0.07
     ste
    -0.07
    q
    -0.07
     Пеш
    -0.07
    Prom
    -0.07
    Editor's
    -0.07
     Dr
    -0.07
    ----------------------------------------------------------------
    -0.07
    POSITIVE LOGITS
    叫什么
    0.11
    是什么
    0.09
     kalau
    0.09
     specialize
    0.09
     المناسب
    0.08
     belangstelling
    0.08
    下载安装
    0.08
     lamun
    0.08
     myaka
    0.08
     właści
    0.08
    Activations Density 0.021%

    No Known Activations