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. 49093
    Prev
    Next
    INDEX
    Explanations

    javascript splice function

    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
    ruid
    -0.08
    블
    -0.08
    omegran
    -0.08
    fb
    -0.07
    تمد
    -0.07
    duck
    -0.07
    客服联系
    -0.07
     नियंत्र
    -0.07
    clin
    -0.07
    opr
    -0.07
    POSITIVE LOGITS
    第一页
    0.08
     padre
    0.08
    [:,
    0.08
     caer
    0.08
    掉
    0.08
     bort
    0.08
     concord
    0.08
    出处
    0.08
     hogar
    0.08
     perspective
    0.08
    Activations Density 0.002%

    No Known Activations