© 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. 18926
    Prev
    Next
    INDEX
    Explanations

    prefix

    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
     divor
    -0.08
     overleden
    -0.08
    ові
    -0.07
    ?page
    -0.07
    ائحة
    -0.07
     BEEN
    -0.07
     Belt
    -0.07
    ί
    -0.07
     fillings
    -0.07
    świ
    -0.07
    POSITIVE LOGITS
     prefix
    0.12
    _prefix
    0.11
    .prefix
    0.11
    Prefix
    0.11
     prefixes
    0.11
     longer
    0.11
    prefix
    0.10
     substr
    0.10
    _try
    0.10
    (prefix
    0.10
    Activations Density 0.005%

    No Known Activations