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. 56095
    Prev
    Next
    INDEX
    Explanations

    formatting/markup

    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
    AFE
    -0.08
    Fors
    -0.08
     ordinarily
    -0.08
     կայ
    -0.07
     SP
    -0.07
     Sf
    -0.07
     व्यव
    -0.07
     voer
    -0.07
     pim
    -0.07
    /he
    -0.07
    POSITIVE LOGITS
    �
    0.07
     Brady
    0.07
     Di
    0.07
    േസമയം
    0.07
    16
    0.07
     grootte
    0.06
     karena
    0.06
     Brug
    0.06
    �
    0.06
     উৎপ
    0.06
    Activations Density 0.155%

    No Known Activations