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. 30607
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     يتعلق
    -0.08
    声明
    -0.08
     девушки
    -0.08
    驻
    -0.08
    ಬ್ಬ
    -0.08
     hazırlan
    -0.08
     แขวง
    -0.08
    ක්ෂ
    -0.07
     recipiente
    -0.07
     милл
    -0.07
    POSITIVE LOGITS
    secure
    0.07
    sn
    0.07
     Burton
    0.07
    plus
    0.06
    очно
    0.06
     Lind
    0.06
     jo
    0.06
    icc
    0.06
    Arithmetic
    0.06
     critically
    0.06
    Activations Density 1.363%

    No Known Activations