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. 90137
    Prev
    Next
    INDEX
    Explanations

    arithmetic 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
     पैदा
    -0.08
     avatar
    -0.08
    avatar
    -0.08
     SX
    -0.08
     oluştur
    -0.08
    already
    -0.07
    -0.07
    ub
    -0.07
    emet
    -0.07
    .'/
    -0.07
    POSITIVE LOGITS
     unspecified
    0.10
     hingegen
    0.09
     unidentified
    0.09
     inconn
    0.09
    UNKNOWN
    0.08
     হয়নি
    0.08
     WARRANT
    0.08
     chưa
    0.08
     என்பது
    0.08
    Maze
    0.08
    Activations Density 0.107%

    No Known Activations