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. 102830
    Prev
    Next
    INDEX
    Explanations

    Math word problems

    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
    Scala
    -0.08
    berg
    -0.07
     regarding
    -0.07
    ".↵↵
    -0.07
     Rh
    -0.07
    Jag
    -0.07
    Ray
    -0.07
    .Js
    -0.07
    360
    -0.07
    -0.07
    POSITIVE LOGITS
     condición
    0.09
     væl
    0.09
     lejos
    0.09
     condição
    0.09
    -cü
    0.09
    超过
    0.08
     excepción
    0.08
    אָט
    0.08
     düzg
    0.08
     deutlich
    0.08
    Activations Density 0.127%

    No Known Activations