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. 53189
    Prev
    Next
    INDEX
    Explanations

    vertex

    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
     unpar
    -0.08
    APE
    -0.07
     iron
    -0.07
     exports
    -0.07
     دلیل
    -0.07
    (heap
    -0.07
     overhaul
    -0.07
    (worker
    -0.07
     تش
    -0.07
     Iron
    -0.07
    POSITIVE LOGITS
    jac
    0.08
     vertex
    0.08
    imum
    0.08
    LOCATION
    0.08
    node
    0.08
    地点
    0.08
     CGPoint
    0.08
     partidos
    0.08
     الطرف
    0.08
     partij
    0.08
    Activations Density 0.010%

    No Known Activations