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. 111680
    Prev
    Next
    INDEX
    Explanations

    随

    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
     suf
    -0.09
     Né
    -0.09
     Willis
    -0.09
     Lact
    -0.08
    preci
    -0.08
     Gore
    -0.08
    unia
    -0.08
    潮
    -0.07
    .ss
    -0.07
     विज
    -0.07
    POSITIVE LOGITS
    �
    0.10
     UA
    0.08
     дел
    0.08
    야
    0.07
     Ve
    0.07
    Beh
    0.07
    ನ್ನು
    0.07
     Beh
    0.07
     Ter
    0.07
     Raven
    0.07
    Activations Density 0.012%

    No Known Activations