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. 98323
    Prev
    Next
    INDEX
    Explanations

    list

    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
     [-
    -0.15
     ["
    -0.13
    [-
    -0.13
     [_
    -0.13
     [['
    -0.12
    ][-
    -0.12
     [`
    -0.12
     [$
    -0.12
     ['
    -0.12
     [["
    -0.12
    POSITIVE LOGITS
     list
    0.09
     பட்ட
    0.09
    _list
    0.09
    ’année
    0.08
     ಪಟ್ಟ
    0.08
    -Date
    0.08
     listed
    0.08
    101
    0.08
     List
    0.08
    _LIST
    0.08
    Activations Density 0.048%

    No Known Activations