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. 44110
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    માંથી
    -0.09
    ಿಗೆ
    -0.08
     Haj
    -0.07
     vaccin
    -0.07
    chall
    -0.07
    Ч
    -0.07
     RF
    -0.07
     Marcus
    -0.07
    થી
    -0.07
     nut
    -0.07
    POSITIVE LOGITS
     وذلك
    0.09
    isons
    0.08
     Leslie
    0.08
     Lle
    0.07
    会上
    0.07
     Amp
    0.07
     basically
    0.07
     यात
    0.07
     forth
    0.07
     JWT
    0.07
    Activations Density 0.307%

    No Known Activations