© 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. 111415
    Prev
    Next
    INDEX
    Explanations

    truth

    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
    Timing
    -0.08
    pea
    -0.07
     acidic
    -0.07
     savvy
    -0.07
    osity
    -0.07
    íc
    -0.07
     timing
    -0.07
     stalk
    -0.07
     tekanan
    -0.07
     Whitney
    -0.07
    POSITIVE LOGITS
     reconciliation
    0.13
     reconc
    0.12
     healing
    0.11
    conciliation
    0.11
     rehabilitation
    0.11
     restorative
    0.10
     Healing
    0.10
     remediation
    0.10
     concili
    0.10
     restit
    0.10
    Activations Density 0.014%

    No Known Activations