© 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 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. 69424
    Prev
    Next
    INDEX
    Explanations

    mandalas

    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
     사항
    -0.08
     recess
    -0.08
     attitude
    -0.07
    -duty
    -0.07
    酸
    -0.07
     accelerator
    -0.07
     landlord
    -0.07
    stones
    -0.07
    েউ
    -0.07
    _HOST
    -0.07
    POSITIVE LOGITS
     ഒരുക്ക
    0.09
     terap
    0.09
     watercolor
    0.08
    .nano
    0.08
    _svg
    0.08
     Peace
    0.08
     Healing
    0.08
    Healing
    0.08
     diagrams
    0.08
     रंग
    0.08
    Activations Density 0.001%

    No Known Activations