© 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. 71150
    Prev
    Next
    INDEX
    Explanations

    .json

    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
    主
    -0.09
    Spe
    -0.07
     主
    -0.07
     xə
    -0.07
     wearing
    -0.07
     uh
    -0.07
     Wol
    -0.07
     VK
    -0.07
     उपाय
    -0.07
     Spe
    -0.07
    POSITIVE LOGITS
    ijão
    0.09
     জম
    0.09
     maker
    0.09
     Grounds
    0.09
    누
    0.08
    .recycle
    0.08
     Maker
    0.08
    minecraft
    0.08
     vermeld
    0.08
     magically
    0.08
    Activations Density 0.005%

    No Known Activations