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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94972
    Prev
    Next
    INDEX
    Explanations

    divided

    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
    িত্র
    -0.08
    Gard
    -0.08
     বৈ
    -0.07
    Iso
    -0.07
     �
    -0.07
     وتج
    -0.07
    द
    -0.07
     Win
    -0.07
    važ
    -0.07
     fen
    -0.07
    POSITIVE LOGITS
     Julio
    0.09
    且
    0.08
     iu
    0.08
     excerpt
    0.08
     discretion
    0.08
    áním
    0.07
     ub
    0.07
    gets
    0.07
    /framework
    0.07
     diren
    0.07
    Activations Density 0.028%

    No Known Activations