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. 109974
    Prev
    Next
    INDEX
    Explanations

    =

    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
     Servers
    -0.08
     Harold
    -0.07
     এই
    -0.07
     Vision
    -0.07
    級
    -0.07
     Logistics
    -0.07
     Construction
    -0.07
     Tooth
    -0.07
     Stainless
    -0.07
     Customer
    -0.07
    POSITIVE LOGITS
     anschließend
    0.08
     nt
    0.08
     subsequently
    0.08
    成果
    0.08
    comfort
    0.08
    自由
    0.08
     unsuccessful
    0.08
     sift
    0.07
     gathered
    0.07
     abl
    0.07
    Activations Density 0.005%

    No Known Activations