© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110660
    Prev
    Next
    INDEX
    Explanations

    Software/System administration

    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
     Cupid
    -0.08
     Beginners
    -0.08
    Volley
    -0.08
     pedal
    -0.08
     femenino
    -0.08
     வீர
    -0.08
    کز
    -0.08
     crédito
    -0.08
     crossover
    -0.08
     महिल
    -0.08
    POSITIVE LOGITS
     installing
    0.13
     installed
    0.13
    Installing
    0.12
    installed
    0.12
     installs
    0.12
     installeren
    0.11
    install
    0.11
    Installed
    0.11
     hostname
    0.11
     installations
    0.11
    Activations Density 0.034%

    No Known Activations