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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2474
    Prev
    Next
    INDEX
    Explanations

    cartesian coordinates in 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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тан
    -0.08
     Hobby
    -0.07
     Wife
    -0.07
     HAM
    -0.07
     headline
    -0.07
    uit
    -0.07
    Pump
    -0.07
     ஹ
    -0.07
     Tuple
    -0.07
     hamp
    -0.07
    POSITIVE LOGITS
     cet
    0.08
     graden
    0.08
     Cet
    0.08
     locus
    0.08
    Cet
    0.08
     feud
    0.08
    。この
    0.08
     lush
    0.07
     Nc
    0.07
     Natura
    0.07
    Activations Density 0.059%

    No Known Activations