© 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. 79386
    Prev
    Next
    INDEX
    Explanations

    tt

    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
    Offering
    -0.08
     sympat
    -0.08
    Refer
    -0.08
    араз
    -0.08
     AIDS
    -0.07
     peat
    -0.07
    _REFER
    -0.07
     Cuba
    -0.07
    Strength
    -0.07
    Ц
    -0.07
    POSITIVE LOGITS
     müd
    0.10
    统一
    0.09
     квартир
    0.09
     திர
    0.08
    修改
    0.08
     automatique
    0.08
     修改
    0.08
     automatische
    0.08
     оформления
    0.08
    _toolbar
    0.08
    Activations Density 0.001%

    No Known Activations