Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11930
    Prev
    Next
    INDEX
    Explanations

    C

    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
    Contest
    -0.09
    contest
    -0.08
     merit
    -0.08
    Distr
    -0.07
    thank
    -0.07
     competent
    -0.07
    decken
    -0.07
     debilit
    -0.07
     delu
    -0.07
     (__
    -0.07
    POSITIVE LOGITS
     BMP
    0.09
    0.08
     steam
    0.08
    接口
    0.08
    .pid
    0.08
     Laser
    0.08
     Steam
    0.08
    äld
    0.07
     വിശദ
    0.07
    mh
    0.07
    Activations Density 0.000%

    No Known Activations