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. 12172
    Prev
    Next
    INDEX
    Explanations

    companies/business

    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
    'b
    -0.07
     Turkish
    -0.07
     tur
    -0.07
     bleeding
    -0.07
     engineer
    -0.07
    'n
    -0.07
     basis
    -0.07
     ak
    -0.07
    qd
    -0.07
    MM
    -0.06
    POSITIVE LOGITS
    FACT
    0.08
     Logger
    0.08
    (logger
    0.08
     Ltd
    0.08
     จำกัด
    0.08
    _cls
    0.08
    iffel
    0.08
    ijing
    0.08
     Hoge
    0.08
    occo
    0.08
    Activations Density 0.253%

    No Known Activations