© 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. 63086
    Prev
    Next
    INDEX
    Explanations

    liability

    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
    筑
    -0.08
     spe
    -0.08
    Spe
    -0.08
     hearty
    -0.08
     cadence
    -0.07
     reliant
    -0.07
    -0.07
     requis
    -0.07
     leer
    -0.07
    بادل
    -0.07
    POSITIVE LOGITS
    患
    0.08
     liabilities
    0.08
    jp
    0.08
     liability
    0.08
     Liability
    0.08
    .iv
    0.07
    inyin
    0.07
    .damage
    0.07
     пи
    0.07
     Comedy
    0.07
    Activations Density 0.004%
    No Known Activations