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. 15-RESID-POST-AA
    6. 19280
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     señalar
    -0.07
     PATH
    -0.07
     inevitably
    -0.07
    �
    -0.07
     respected
    -0.07
    ుంది
    -0.07
    )↵↵↵
    -0.07
     &_
    -0.07
     overwhelmingly
    -0.07
    чи
    -0.07
    POSITIVE LOGITS
     deutsch
    0.11
     foodie
    0.10
    在哪里买
    0.10
    Affordable
    0.10
     deutschen
    0.10
     भन्न
    0.10
    哪个好
    0.10
     shqiptar
    0.10
     Azərbaycan
    0.10
     Affordable
    0.09
    Activations Density 0.008%

    No Known Activations