© 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. 63018
    Prev
    Next
    INDEX
    Explanations

    WPA

    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
     dư
    -0.09
     útiles
    -0.08
     crush
    -0.08
    腹
    -0.08
     Turk
    -0.08
    .lbl
    -0.08
     dil
    -0.08
    _dom
    -0.08
     observational
    -0.08
    ceased
    -0.08
    POSITIVE LOGITS
     WPA
    0.11
     signed
    0.09
    Credential
    0.09
     Credential
    0.09
    Authentication
    0.08
    Credentials
    0.08
     authentication
    0.08
    signed
    0.08
     Signed
    0.08
    Requires
    0.08
    Activations Density 0.005%

    No Known Activations