© 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. 25898
    Prev
    Next
    INDEX
    Explanations

    Remote work

    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
    增强
    -0.09
     utilisateur
    -0.08
    LOSS
    -0.08
     utilisateurs
    -0.08
     접근
    -0.08
     personne
    -0.08
     blasts
    -0.08
     opération
    -0.08
    'utilisateur
    -0.08
     underpin
    -0.08
    POSITIVE LOGITS
     Russo
    0.09
     bij
    0.09
     ansi
    0.08
     Worldwide
    0.08
    _dims
    0.08
     Bloomberg
    0.08
     weltweit
    0.08
     atrop
    0.08
     worldwide
    0.07
     mist
    0.07
    Activations Density 0.002%

    No Known Activations