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. 58648
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    _upper
    -0.08
    低
    -0.08
     anty
    -0.07
     বহ
    -0.07
    brit
    -0.07
     duy
    -0.07
     ಅನ್ನು
    -0.07
     Esq
    -0.07
    Unsupported
    -0.07
    sas
    -0.07
    POSITIVE LOGITS
     attackers
    0.09
    发动
    0.08
     berühm
    0.08
     aggiorn
    0.08
     famous
    0.08
     знаменит
    0.08
     부탁
    0.08
     prolific
    0.08
    -born
    0.07
    、中国
    0.07
    Activations Density 0.139%

    No Known Activations