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. 88236
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     legalized
    -0.08
    ക്ക
    -0.08
    ESCO
    -0.08
    为空
    -0.08
    น
    -0.07
     നിയമ
    -0.07
     വര
    -0.07
    പ്പ
    -0.07
    หน้
    -0.07
    പ
    -0.07
    POSITIVE LOGITS
     Supplemental
    0.07
     Seconds
    0.07
     optimism
    0.07
     persuaded
    0.07
    798
    0.07
     fingert
    0.07
    475
    0.07
    �
    0.07
    Think
    0.07
     rere
    0.07
    Activations Density 0.107%

    No Known Activations