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. 23-RESID-POST-AA
    6. 98494
    Prev
    Next
    INDEX
    Explanations

    Greetings and thanks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    начала
    -0.08
    First
    -0.08
     først
    -0.08
     outset
    -0.08
    Tijdens
    -0.08
     eerste
    -0.07
    ’abord
    -0.07
     dahulu
    -0.07
     ensimmä
    -0.07
    -первых
    -0.07
    POSITIVE LOGITS
     Stay
    0.19
     Cheers
    0.18
    ありがとうございました
    0.18
    Cheers
    0.18
     Danke
    0.18
     Спасибо
    0.17
     Thank
    0.17
     धन्यवाद
    0.17
    Stay
    0.17
    Спасибо
    0.17
    Activations Density 0.046%

    No Known Activations