© 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. 70626
    Prev
    Next
    INDEX
    Explanations

    saturated

    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
     سد
    -0.08
     Cri
    -0.08
     Panther
    -0.07
     Soc
    -0.07
    ś
    -0.07
    Soc
    -0.07
    صر
    -0.07
    Work
    -0.07
     Nov
    -0.07
     Armstrong
    -0.07
    POSITIVE LOGITS
     exagger
    0.10
     exaggerated
    0.10
     exager
    0.09
     hues
    0.09
     mạnh
    0.09
     amplify
    0.08
    -semibold
    0.08
    amines
    0.08
     colors
    0.08
    006
    0.08
    Activations Density 0.001%

    No Known Activations