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. 30645
    Prev
    Next
    INDEX
    Explanations

    apprentice

    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
     notific
    -0.08
    达人
    -0.07
     rhin
    -0.07
     मू
    -0.07
    品质
    -0.07
     nectar
    -0.07
     papar
    -0.07
    通常
    -0.07
     peach
    -0.07
     preset
    -0.07
    POSITIVE LOGITS
     Soc
    0.08
     Scha
    0.08
    Soc
    0.08
     пись
    0.08
     Siber
    0.08
     iron
    0.07
     enrolling
    0.07
    hips
    0.07
     Tabla
    0.07
     Aya
    0.07
    Activations Density 0.002%

    No Known Activations