Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 60819
    Prev
    Next
    INDEX
    Explanations

    when

    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
    oan
    -0.08
     Debt
    -0.07
     ail
    -0.07
    حل
    -0.07
     fortress
    -0.07
     upfront
    -0.07
     만드는
    -0.07
     distracted
    -0.07
     банков
    -0.07
     bank
    -0.07
    POSITIVE LOGITS
    -là
    0.13
    -called
    0.09
    soy
    0.08
    İ
    0.08
     thấy
    0.08
     Minder
    0.08
    此
    0.08
     Pedro
    0.08
     Coimbra
    0.08
    Bart
    0.08
    Activations Density 0.058%

    No Known Activations