© 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. 91831
    Prev
    Next
    INDEX
    Explanations

    braces

    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
     slogan
    -0.07
     marched
    -0.07
     commander
    -0.07
     mindset
    -0.07
    wan
    -0.07
    ہم
    -0.07
    LG
    -0.07
     Planner
    -0.07
    -duty
    -0.07
     Gat
    -0.07
    POSITIVE LOGITS
     teil
    0.08
     meadow
    0.08
    858
    0.08
     qab
    0.08
     gemeins
    0.08
     aktu
    0.08
     wiadomo
    0.08
     danych
    0.07
    alled
    0.07
     upto
    0.07
    Activations Density 0.026%

    No Known Activations