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. 98447
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .har
    -0.08
     stew
    -0.08
    uper
    -0.08
     vault
    -0.07
     cas
    -0.07
     kalah
    -0.07
     Phoenix
    -0.07
    超级
    -0.07
     ən
    -0.07
    ,与
    -0.07
    POSITIVE LOGITS
     derece
    0.08
     принят
    0.08
     conceb
    0.08
     փոխանց
    0.08
    _FORMAT
    0.08
    ACING
    0.08
     привыч
    0.08
    ๑
    0.08
     placing
    0.08
     формат
    0.08
    Activations Density 0.001%

    No Known Activations