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. 15-RESID-POST-AA
    6. 19550
    Prev
    Next
    INDEX
    Explanations

    prompt

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kafin
    -0.09
     Leap
    -0.09
    为了
    -0.08
    _Copy
    -0.08
    Leap
    -0.08
    ugq
    -0.08
     quoi
    -0.08
     ukuf
    -0.08
     õpp
    -0.07
     convierte
    -0.07
    POSITIVE LOGITS
     specifics
    0.08
     extender
    0.08
                                                       
    0.08
                                           
    0.07
     specifying
    0.07
    =$(
    0.07
     detailing
    0.07
     specif
    0.07
     Prev
    0.07
                                                      
    0.07
    Activations Density 0.002%

    No Known Activations