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. 44449
    Prev
    Next
    INDEX
    Explanations

    bar

    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
    unc
    -0.09
     zij
    -0.08
     نها
    -0.08
     zach
    -0.07
    وائد
    -0.07
     النهائي
    -0.07
    ilios
    -0.07
     quir
    -0.07
    -over
    -0.07
     koelkast
    -0.07
    POSITIVE LOGITS
     পর্যন্ত
    0.08
    压
    0.08
    .bet
    0.07
     వద్ద
    0.07
    \,
    0.07
    ^-
    0.07
    RX
    0.07
     Hive
    0.07
     വരെ
    0.07
     ago
    0.07
    Activations Density 0.003%

    No Known Activations