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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 42025
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     servant
    -0.09
     അന്വേഷ
    -0.09
    SEM
    -0.08
     быст
    -0.08
     binocular
    -0.08
    สอบ
    -0.08
     люб
    -0.08
     гуман
    -0.08
     searching
    -0.08
     расслед
    -0.08
    POSITIVE LOGITS
     chmod
    0.08
    �
    0.08
    呵
    0.08
     kali
    0.08
    �
    0.08
    辰
    0.07
     التشغيل
    0.07
     vezes
    0.07
     Voyage
    0.07
    盾
    0.07
    Activations Density 0.045%

    No Known Activations