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. 12170
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     mera
    -0.08
    通讯
    -0.08
    販
    -0.08
     medic
    -0.07
     �
    -0.07
     తద
    -0.07
    elo
    -0.07
    创新
    -0.07
     abst
    -0.07
    称
    -0.07
    POSITIVE LOGITS
    ಬ
    0.08
    	the
    0.07
     جاء
    0.07
    צע
    0.07
     realiza
    0.07
    قدم
    0.07
     jumbo
    0.07
    <ul
    0.07
     Critical
    0.07
    फ़
    0.07
    Activations Density 0.035%

    No Known Activations