© 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. 15-RESID-POST-AA
    11. 16277
    Prev
    Next
    INDEX
    Explanations

    way/manner

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     প্ৰ
    -0.08
    ren
    -0.07
    μαι
    -0.07
    leo
    -0.07
     Moody
    -0.07
     ম
    -0.07
    vier
    -0.07
     ধরনের
    -0.07
    estic
    -0.07
     wisely
    -0.07
    POSITIVE LOGITS
    -साथ
    0.10
     توګه
    0.10
     وعلى
    0.09
    冊
    0.08
     соответствии
    0.08
     וב
    0.08
     versuchen
    0.08
    Кроме
    0.08
     وكذلك
    0.08
    ،
    0.08
    Activations Density 0.126%

    No Known Activations