© 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. 11-RESID-POST-AA
    11. 94464
    Prev
    Next
    INDEX
    Explanations

    code and reference materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ondernem
    -0.07
     муж
    -0.07
     Pops
    -0.07
     slab
    -0.07
     Randall
    -0.07
     nois
    -0.07
     mors
    -0.06
     preferable
    -0.06
     Tari
    -0.06
     fuck
    -0.06
    POSITIVE LOGITS
    整理
    0.08
     lọ
    0.08
     moje
    0.07
     Eins
    0.07
     doctr
    0.07
    筛
    0.07
     prév
    0.07
    даў
    0.07
     ঐ
    0.07
     anthology
    0.07
    Activations Density 27.654%

    No Known Activations