© 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. 108300
    Prev
    Next
    INDEX
    Explanations

    lens

    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
    lerden
    -0.08
    ್ಲ
    -0.08
     temel
    -0.08
    tren
    -0.08
     évalu
    -0.08
     Angehör
    -0.07
    ذية
    -0.07
     rappresent
    -0.07
    ేట
    -0.07
     பகுத
    -0.07
    POSITIVE LOGITS
     cybers
    0.08
    OD
    0.08
    illard
    0.07
    Ё
    0.07
     blag
    0.07
     twilight
    0.07
     MSD
    0.07
    spd
    0.07
    Stor
    0.07
    Odds
    0.07
    Activations Density 0.000%

    No Known Activations