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. 88103
    Prev
    Next
    INDEX
    Explanations

    latex and math equations

    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
     alls
    -0.10
     variation
    -0.08
     onth
    -0.08
     varie
    -0.08
    -var
    -0.08
    landa
    -0.08
     aload
    -0.08
    之外
    -0.08
     luar
    -0.08
    ーズ
    -0.08
    POSITIVE LOGITS
    eshimiwa
    0.08
     investigar
    0.08
    Topic
    0.07
    Investig
    0.07
    Subtitle
    0.07
     речь
    0.07
    Task
    0.07
    Describe
    0.07
     calcular
    0.07
     requested
    0.07
    Activations Density 0.029%

    No Known Activations