© 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. 19-RESID-POST-AA
    11. 18744
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *
    -0.10
    handle
    -0.08
     did
    -0.08
    _handle
    -0.08
     **
    -0.08
     però
    -0.07
     divided
    -0.07
    وقد
    -0.07
    did
    -0.07
    .common
    -0.07
    POSITIVE LOGITS
     Exists
    0.09
     sustit
    0.09
    Replace
    0.08
     Sistem
    0.08
     Replace
    0.08
     finns
    0.08
     Programs
    0.08
     ഉണ്ട
    0.08
     Having
    0.08
     Nearby
    0.08
    Activations Density 0.008%

    No Known Activations