© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 49046
    Prev
    Next
    INDEX
    Explanations

    say "logged and authenticated"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urlpatterns
    -0.09
    utton
    -0.08
    @Xml
    -0.08
     migration
    -0.08
    >Password
    -0.08
     retrans
    -0.07
     xtype
    -0.07
     chicken
    -0.07
     rashin
    -0.07
    _nodes
    -0.07
    POSITIVE LOGITS
     logged
    0.18
    Logged
    0.17
     authenticated
    0.16
     Logged
    0.16
    .logged
    0.15
    _logged
    0.15
    _authenticated
    0.15
    Authenticated
    0.15
    logged
    0.15
    authenticated
    0.14
    Activations Density 0.008%

    No Known Activations