Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58405
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    icc
    -0.08
    ngel
    -0.08
     האל
    -0.08
    ಗಳಲ್ಲಿ
    -0.08
     espont
    -0.08
    .term
    -0.08
     Mutter
    -0.07
    ೀನ
    -0.07
     впечат
    -0.07
    .family
    -0.07
    POSITIVE LOGITS
     stöd
    0.08
     boob
    0.08
    KE
    0.08
     EOS
    0.08
    جون
    0.08
    cki
    0.07
    gow
    0.07
     solution
    0.07
     tob
    0.07
     insecure
    0.07
    Activations Density 0.127%

    No Known Activations