© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102550
    Prev
    Next
    INDEX
    Explanations

    complex

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    истема
    -0.09
     jeweiligen
    -0.08
    енең
    -0.08
    иниң
    -0.08
     correspondiente
    -0.08
    ುತ್ತ
    -0.08
    ocused
    -0.08
     entsprechenden
    -0.07
    естиваль
    -0.07
    Sistema
    -0.07
    POSITIVE LOGITS
    复杂
    0.22
     complex
    0.22
     Complex
    0.19
     komplex
    0.18
    Complex
    0.18
     complexe
    0.18
    _complex
    0.18
    complex
    0.18
     слож
    0.17
     ingewikk
    0.17
    Activations Density 0.043%

    No Known Activations