© 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. 70508
    Prev
    Next
    INDEX
    Explanations

    ad

    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
     Beh
    -0.08
     svega
    -0.08
    -dire
    -0.07
     நண்ப
    -0.07
    Beh
    -0.07
     indications
    -0.07
     vriend
    -0.07
    veranst
    -0.07
     wakes
    -0.07
    。截至
    -0.07
    POSITIVE LOGITS
     sham
    0.08
    _IMAGE
    0.08
     destinados
    0.08
    产生
    0.07
    =(
    0.07
     issus
    0.07
     cárcel
    0.07
    idata
    0.07
    #endif
    0.07
    ộc
    0.07
    Activations Density 0.021%

    No Known Activations