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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 43776
    Prev
    Next
    INDEX
    Explanations

    Medical body text

    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
    plug
    -0.08
    达人
    -0.08
     achievable
    -0.08
     griff
    -0.08
    ADC
    -0.08
     attainable
    -0.07
     attained
    -0.07
     cens
    -0.07
     ausência
    -0.07
    鼎
    -0.07
    POSITIVE LOGITS
     സിനിമ
    0.08
     Invisible
    0.08
     ചെ
    0.08
     нерв
    0.08
     peso
    0.08
     arteries
    0.08
     Ruth
    0.07
    ുള്ള
    0.07
     дорог
    0.07
    Lights
    0.07
    Activations Density 0.003%

    No Known Activations