© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71216
    Prev
    Next
    INDEX
    Explanations

    securities

    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
     sailors
    -0.08
     الشعر
    -0.07
    äne
    -0.07
     Wenger
    -0.07
     pura
    -0.07
     horm
    -0.07
     pilgrims
    -0.07
     dim
    -0.07
     автомобили
    -0.07
     dancers
    -0.07
    POSITIVE LOGITS
    .Cache
    0.08
    -assisted
    0.07
     atuação
    0.07
     concluded
    0.07
    번호
    0.07
     development
    0.07
     nimi
    0.07
    otechnology
    0.07
     논
    0.07
     ಸಂಸ್ಥ
    0.07
    Activations Density 0.003%

    No Known Activations