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. 45081
    Prev
    Next
    INDEX
    Explanations

    CPUs

    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
    וש
    -0.08
     रिस
    -0.08
     Document
    -0.08
     visu
    -0.07
     pren
    -0.07
     recop
    -0.07
     resin
    -0.07
     सुव
    -0.07
     prerequisites
    -0.07
     troubleshoot
    -0.07
    POSITIVE LOGITS
    -custom
    0.09
     summoned
    0.08
     hybride
    0.08
    уры
    0.08
     hybr
    0.08
    Modified
    0.08
    harap
    0.08
     officers
    0.08
    னி
    0.08
    Hybrid
    0.08
    Activations Density 0.004%

    No Known Activations