© 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. 111442
    Prev
    Next
    INDEX
    Explanations

    numerical computations

    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
    Castle
    -0.08
    House
    -0.08
     cheer
    -0.08
    eret
    -0.08
    Featured
    -0.08
     disguised
    -0.08
     HOUSE
    -0.08
    ים
    -0.08
    Administrative
    -0.08
     administrative
    -0.08
    POSITIVE LOGITS
     neutron
    0.10
    _pressure
    0.10
     ವಿದ್ಯ
    0.10
     centimeter
    0.09
     liters
    0.09
     Hz
    0.09
     Eq
    0.09
     Photon
    0.09
     GHz
    0.09
     Fender
    0.09
    Activations Density 0.029%

    No Known Activations