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. 43082
    Prev
    Next
    INDEX
    Explanations

    idx

    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
     antibiotic
    -0.08
    dust
    -0.07
    _blue
    -0.07
     extracellular
    -0.07
    _pdf
    -0.07
    ာ
    -0.07
     صاف
    -0.07
     vooraf
    -0.07
     certeza
    -0.07
     diar
    -0.07
    POSITIVE LOGITS
     elems
    0.09
     priority
    0.08
     recruiters
    0.08
    ulog
    0.08
    (priority
    0.08
    .elem
    0.08
     부모
    0.08
     elem
    0.08
    gevallen
    0.08
     uint
    0.08
    Activations Density 0.003%

    No Known Activations