© 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. 16357
    Prev
    Next
    INDEX
    Explanations

    Tables of data

    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
    -Tr
    -0.08
     p
    -0.08
     konkret
    -0.08
    289
    -0.07
     dép
    -0.07
     vir
    -0.07
     arbitrary
    -0.07
    -tr
    -0.07
     jeho
    -0.07
    ::
    -0.07
    POSITIVE LOGITS
     elsif
    0.09
     elseif
    0.09
     նույնպես
    0.09
     এসব
    0.09
    ಲಾಗಿದೆ
    0.08
     nämä
    0.08
    یسے
    0.08
    色综合
    0.08
     exhibitors
    0.08
    adhna
    0.08
    Activations Density 0.018%

    No Known Activations