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. 388
    Prev
    Next
    INDEX
    Explanations

    /

    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
    etur
    -0.09
    teri
    -0.08
    産
    -0.07
    Keeper
    -0.07
     Minder
    -0.07
    %\
    -0.07
     Username
    -0.07
     Sonn
    -0.07
    留言
    -0.07
    Ung
    -0.07
    POSITIVE LOGITS
    ½
    0.10
    ¾
    0.09
     tablespoons
    0.09
    აქც
    0.09
    ¼
    0.09
     ಗಂಟ
    0.08
     ansin
    0.08
     рань
    0.08
     ïa
    0.08
     ஸ
    0.08
    Activations Density 0.010%

    No Known Activations