© 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. 63631
    Prev
    Next
    INDEX
    Explanations

    Activities

    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
    иқ
    -0.08
    _disc
    -0.08
    _partition
    -0.08
     الكشف
    -0.08
    েড
    -0.08
    disc
    -0.08
    әгән
    -0.08
    әлар
    -0.08
    énement
    -0.08
    Ա
    -0.08
    POSITIVE LOGITS
     wheelchair
    0.11
     ondanks
    0.09
     malgré
    0.09
     trotz
    0.09
     Despite
    0.09
     Disability
    0.09
     despite
    0.08
     ix
    0.08
     spite
    0.08
     ike
    0.07
    Activations Density 0.071%

    No Known Activations