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. 43739
    Prev
    Next
    INDEX
    Explanations

    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
    지
    -0.08
     formulas
    -0.08
    andan
    -0.07
    rand
    -0.07
    ării
    -0.07
     musicals
    -0.07
     imput
    -0.07
     Historically
    -0.07
     musical
    -0.07
    ourse
    -0.07
    POSITIVE LOGITS
     _,
    0.08
    (_,
    0.08
    (sender
    0.08
     utan
    0.07
     начиная
    0.07
     Huntington
    0.07
     ceremon
    0.07
     показ
    0.07
    ycle
    0.07
     evo
    0.07
    Activations Density 0.002%

    No Known Activations