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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 49236
    Prev
    Next
    INDEX
    Explanations

    Math track 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
     utilizar
    -0.08
    fits
    -0.08
    Journal
    -0.07
    สำหรับ
    -0.07
     fits
    -0.07
    Branch
    -0.07
    જી
    -0.07
    რძ
    -0.07
     conect
    -0.07
     Agricultural
    -0.07
    POSITIVE LOGITS
    .Inv
    0.10
    ynchron
    0.09
     ping
    0.09
     swarm
    0.09
     घूम
    0.09
     oscill
    0.09
     धी
    0.09
     periodically
    0.08
    clock
    0.08
     synchronization
    0.08
    Activations Density 0.013%

    No Known Activations