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. 65774
    Prev
    Next
    INDEX
    Explanations

    code and equations

    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
     dopu
    -0.08
     줄
    -0.08
     સ્થળ
    -0.08
     Cof
    -0.08
     cof
    -0.08
     fè
    -0.08
     �
    -0.07
     그렇게
    -0.07
     ಸ್ಥಳ
    -0.07
     шел
    -0.07
    POSITIVE LOGITS
    	timer
    0.09
     Wizards
    0.08
    				
    ↵
    0.08
    viral
    0.08
    				↵
    0.07
    ']));↵
    0.07
    Aval
    0.07
    Alliance
    0.07
    Solo
    0.07
    _timer
    0.07
    Activations Density 0.000%

    No Known Activations