© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1384
    Prev
    Next
    INDEX
    Explanations

    ancestors/parents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provision
    -0.08
     provisions
    -0.08
     endpoints
    -0.08
     alloy
    -0.08
     Provision
    -0.08
    Provision
    -0.07
     barrels
    -0.07
     punta
    -0.07
     развед
    -0.07
     порядок
    -0.07
    POSITIVE LOGITS
     enclosing
    0.09
    (parent
    0.09
     parent
    0.08
    .parent
    0.08
    (Context
    0.08
     context
    0.08
     UILabel
    0.08
     பொர
    0.07
    親
    0.07
    父
    0.07
    Activations Density 0.003%

    No Known Activations