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. 112494
    Prev
    Next
    INDEX
    Explanations

    heading

    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
     becoming
    -0.07
     बनने
    -0.07
     swal
    -0.07
    利用
    -0.07
     stature
    -0.07
    �
    -0.07
     multitude
    -0.06
     Utilize
    -0.06
    排行榜
    -0.06
     七彩
    -0.06
    POSITIVE LOGITS
    ices
    0.09
    gments
    0.08
     Elig
    0.08
     indiqu
    0.08
     Hon
    0.08
    =("
    0.08
    gements
    0.08
     indique
    0.07
     Vehicles
    0.07
    =('
    0.07
    Activations Density 0.002%

    No Known Activations