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. 103
    Prev
    Next
    INDEX
    Explanations

    Legal, law

    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
     شاید
    -0.10
     cartoon
    -0.10
     אולי
    -0.10
    ılıyor
    -0.10
     bunny
    -0.10
     رائع
    -0.10
     :-)↵↵
    -0.10
     gummies
    -0.10
     ډیر
    -0.10
     אנשים
    -0.10
    POSITIVE LOGITS
    依法
    0.16
     pursuant
    0.14
     statutory
    0.14
     lawful
    0.14
     jurisprud
    0.13
     unlaw
    0.13
     संविधान
    0.13
     judicial
    0.13
     (§
    0.12
    司法
    0.12
    Activations Density 0.062%

    No Known Activations