© 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. 799
    Prev
    Next
    INDEX
    Explanations

    maybe

    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
     waard
    -0.09
     aparentemente
    -0.08
    Occupied
    -0.08
    Equal
    -0.08
    hen
    -0.08
     aucune
    -0.08
    quired
    -0.08
    _as
    -0.08
     supposedly
    -0.08
    /ou
    -0.07
    POSITIVE LOGITS
     Scandinavian
    0.09
     sentences
    0.09
    先
    0.08
     recap
    0.08
     Clan
    0.08
     Scandin
    0.08
     Tuscany
    0.08
     disclaim
    0.08
     ange
    0.08
     paragraph
    0.08
    Activations Density 0.076%

    No Known Activations