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. 129787
    Prev
    Next
    INDEX
    Explanations

    hands

    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
    (desc
    -0.08
    Physics
    -0.08
    Federal
    -0.08
     Vorsitz
    -0.07
    physics
    -0.07
    Jenis
    -0.07
    _master
    -0.07
    'ident
    -0.07
    'description
    -0.07
    ran
    -0.07
    POSITIVE LOGITS
     اليد
    0.09
     рук
    0.08
    생활
    0.08
     шул
    0.08
     взять
    0.08
     கை
    0.08
    황
    0.08
     luxurious
    0.08
     перенос
    0.08
     cá
    0.07
    Activations Density 0.003%

    No Known Activations