Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58586
    Prev
    Next
    INDEX
    Explanations

    2

    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
    Displayed
    -0.09
     displayed
    -0.08
     bie
    -0.07
    axed
    -0.07
     verlichting
    -0.07
     Fiona
    -0.07
     ausreichend
    -0.07
    好多
    -0.07
     traduction
    -0.07
     affich
    -0.07
    POSITIVE LOGITS
     predecessor
    0.11
     successor
    0.10
     predecessors
    0.09
     stencil
    0.09
     successors
    0.08
     Shock
    0.08
    Shock
    0.08
     استقلال
    0.08
     spouse
    0.08
    _operator
    0.08
    Activations Density 0.022%

    No Known Activations