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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98685
    Prev
    Next
    INDEX
    Explanations

    Krishna

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enix
    -0.08
     gip
    -0.08
     дипломат
    -0.07
    ചന
    -0.07
    额度
    -0.07
    hag
    -0.07
    Apps
    -0.07
    ാങ
    -0.07
     angels
    -0.07
    ాచ్
    -0.07
    POSITIVE LOGITS
    ishna
    0.11
    ish
    0.09
     stuffed
    0.08
    िहर
    0.08
    ושי
    0.08
     इंड
    0.08
    充
    0.08
    ighi
    0.08
     filled
    0.08
    ISH
    0.07
    Activations Density 0.000%

    No Known Activations