© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64351
    Prev
    Next
    INDEX
    Explanations

    programming and rules

    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
    mas
    -0.08
     тези
    -0.07
    Immer
    -0.07
    209
    -0.07
    Epic
    -0.07
     многочис
    -0.07
     Philharm
    -0.07
    instr
    -0.07
     päivän
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     called
    0.13
     namens
    0.11
     يسمى
    0.11
     appelée
    0.11
     হিসেবে
    0.10
    として
    0.10
    之一
    0.10
     તરીકે
    0.10
     chiam
    0.09
     म्हणून
    0.09
    Activations Density 0.118%

    No Known Activations