© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16338
    Prev
    Next
    INDEX
    Explanations

    code markers

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulled
    -0.08
     unmarried
    -0.08
     qilib
    -0.08
     широкий
    -0.07
     vielf
    -0.07
     rushed
    -0.07
     dominated
    -0.07
     outreach
    -0.07
     interviewed
    -0.07
     overwhelmingly
    -0.07
    POSITIVE LOGITS
    @Retention
    0.13
     markers
    0.13
    Marker
    0.12
     marker
    0.12
    .marker
    0.12
    Directive
    0.11
    marker
    0.11
     directives
    0.11
    -marker
    0.11
    Markers
    0.11
    Activations Density 0.019%

    No Known Activations