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. 65818
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    'énergie
    -0.08
    ojen
    -0.08
    、公
    -0.08
     project's
    -0.07
     firm's
    -0.07
    riteln
    -0.07
    динг
    -0.07
    дается
    -0.07
     lifelong
    -0.07
     Beaut
    -0.07
    POSITIVE LOGITS
     fila
    0.08
    型号
    0.08
    ulator
    0.07
     pickle
    0.07
    icon
    0.07
     elem
    0.07
     quadrant
    0.07
     Kaiser
    0.07
    binations
    0.07
     apt
    0.07
    Activations Density 0.008%

    No Known Activations