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. 112141
    Prev
    Next
    INDEX
    Explanations

    核

    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
    ancis
    -0.08
     Creo
    -0.08
    ಲ್ಲಿ
    -0.07
     clair
    -0.07
    غة
    -0.07
     дил
    -0.07
     completo
    -0.07
    idele
    -0.07
     Gardner
    -0.07
    992
    -0.07
    POSITIVE LOGITS
    素
    0.08
    Grab
    0.08
     Spike
    0.08
    વણી
    0.07
    hardt
    0.07
     Hog
    0.07
     Bav
    0.07
    �
    0.07
     chamber
    0.07
     Exped
    0.07
    Activations Density 0.008%

    No Known Activations