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. 97098
    Prev
    Next
    INDEX
    Explanations

    方

    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
     सिक
    -0.08
    CQ
    -0.08
    ူး
    -0.08
    クラ
    -0.08
     இர
    -0.08
     テ
    -0.07
     बे
    -0.07
     breit
    -0.07
    プレ
    -0.07
    _sv
    -0.07
    POSITIVE LOGITS
    程
    0.25
    程序
    0.17
     �
    0.13
    ほど
    0.13
     trình
    0.13
    程序集
    0.10
     proqram
    0.09
     programmi
    0.09
     Program
    0.09
    programma
    0.08
    Activations Density 0.001%

    No Known Activations