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. 54005
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    ран
    -0.08
     telle
    -0.08
     meisten
    -0.08
    ертв
    -0.08
     demasi
    -0.07
     maggior
    -0.07
    )">
    -0.07
     maggiore
    -0.07
     Rabb
    -0.07
     BT
    -0.07
    POSITIVE LOGITS
    且
    0.10
    並
    0.09
     בלבד
    0.08
    ਸੀ
    0.08
    ,并
    0.08
    か
    0.08
    并
    0.07
     නො
    0.07
    ,而且
    0.07
    කි
    0.07
    Activations Density 0.236%

    No Known Activations