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. 60849
    Prev
    Next
    INDEX
    Explanations

    pages

    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
     fırs
    -0.08
    ech
    -0.08
     partner
    -0.08
     freezed
    -0.08
    -0.07
     ocasi
    -0.07
     nəz
    -0.07
     партнер
    -0.07
     partners
    -0.07
     trays
    -0.07
    POSITIVE LOGITS
    を書く
    0.09
     વાંચ
    0.09
    読
    0.08
    annen
    0.08
    -blog
    0.08
    AAD
    0.08
    Story
    0.08
    .Character
    0.08
     autobiography
    0.08
    왔다
    0.08
    Activations Density 0.007%

    No Known Activations