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. 78626
    Prev
    Next
    INDEX
    Explanations

    fractions and math

    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
     permanence
    -0.08
     varying
    -0.08
     Illuminate
    -0.07
     launches
    -0.07
     manners
    -0.07
     legality
    -0.07
    levant
    -0.07
     []*
    -0.07
    configs
    -0.07
     '/'
    -0.07
    POSITIVE LOGITS
    Percentage
    0.08
    Approximately
    0.08
     Belgische
    0.08
     perfekt
    0.08
     erinnern
    0.08
     ശതമ
    0.08
     प्रतिशत
    0.08
     πισ
    0.08
    _RATIO
    0.08
     Approx
    0.08
    Activations Density 0.024%

    No Known Activations