© 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. 31521
    Prev
    Next
    INDEX
    Explanations

    phrase

    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
    jl
    -0.08
     conscious
    -0.08
     tej
    -0.08
    579
    -0.08
    _posts
    -0.07
     حاجة
    -0.07
    익
    -0.07
     DJs
    -0.07
     zie
    -0.07
     આ
    -0.07
    POSITIVE LOGITS
    ว่า
    0.09
    Thi
    0.08
    0.08
     glasses
    0.08
     phr
    0.08
     Kenny
    0.08
    ور
    0.08
     coined
    0.08
     بالا
    0.07
    ांश
    0.07
    Activations Density 0.023%
    No Known Activations