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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 64961
    Prev
    Next
    INDEX
    Explanations

    of

    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
    GNU
    -0.08
    wrapper
    -0.07
    ll
    -0.07
     memper
    -0.07
     GNU
    -0.07
    NG
    -0.07
    combat
    -0.07
    en
    -0.07
    TOOLS
    -0.07
    ffff
    -0.07
    POSITIVE LOGITS
     אי
    0.09
     декоратив
    0.08
     Kaw
    0.08
     widths
    0.08
     આવા
    0.08
     Owens
    0.08
    ևէ
    0.08
     ساعات
    0.08
    .instance
    0.07
    եկտ
    0.07
    Activations Density 0.018%

    No Known Activations