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. 11-RESID-POST-AA
    6. 53984
    Prev
    Next
    INDEX
    Explanations

    instructions or advice

    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
    DEFAULT
    -0.08
    .mouse
    -0.07
    _STATIC
    -0.07
    =A
    -0.07
     currency
    -0.07
     Wärme
    -0.07
     SAF
    -0.07
    _ACCESS
    -0.07
    CODE
    -0.07
    .DEFAULT
    -0.07
    POSITIVE LOGITS
    什么时候
    0.15
     cuándo
    0.14
     جڏهن
    0.14
     nigbati
    0.11
     عندما
    0.11
     nuair
    0.11
     ત્યારે
    0.11
     wanneer
    0.11
     кога
    0.11
     wann
    0.11
    Activations Density 0.078%

    No Known Activations