© 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. 31342
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities

    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
     Enhanced
    -0.09
     hrs
    -0.09
    Enhanced
    -0.08
     ونه
    -0.08
     Гол
    -0.08
     مخ
    -0.08
     parejas
    -0.07
     GOOD
    -0.07
     乐
    -0.07
    hrs
    -0.07
    POSITIVE LOGITS
     wiederum
    0.10
     excerpt
    0.09
     hierarchical
    0.08
     glycer
    0.08
     tetra
    0.07
     Mustafa
    0.07
     nghiên
    0.07
    шин
    0.07
    maken
    0.07
     passi
    0.07
    Activations Density 0.033%

    No Known Activations