© 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. 16658
    Prev
    Next
    INDEX
    Explanations

    narrative

    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
    &nbsp
    -0.08
     â
    -0.08
     (=
    -0.08
     harmless
    -0.07
    quired
    -0.07
    .jsp
    -0.07
     {{
    -0.07
    &apos
    -0.07
    &quot
    -0.07
    。据
    -0.07
    POSITIVE LOGITS
     narr
    0.13
     कथा
    0.12
     narrative
    0.12
     కథ
    0.12
     постепенно
    0.11
     climax
    0.11
     gradually
    0.11
    小說
    0.11
     excerpts
    0.11
     روایت
    0.11
    Activations Density 0.047%

    No Known Activations