© 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. 79422
    Prev
    Next
    INDEX
    Explanations

    commas and ampersands

    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
     ignorance
    -0.08
     subconscious
    -0.08
     blindly
    -0.08
     desperately
    -0.08
     substitutes
    -0.08
    -but
    -0.08
    -all
    -0.08
    ⠀⠀
    -0.07
     insists
    -0.07
     inoc
    -0.07
    POSITIVE LOGITS
     특징
    0.13
    特点
    0.13
    特色
    0.12
     noteworthy
    0.10
     notable
    0.10
     особен
    0.10
    特徴
    0.09
    Awards
    0.09
     Awards
    0.09
     주요
    0.09
    Activations Density 0.077%

    No Known Activations