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. 53120
    Prev
    Next
    INDEX
    Explanations

    function and memory

    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
    非法
    -0.08
     jpg
    -0.08
     Copier
    -0.08
     tanker
    -0.08
     lash
    -0.08
     London's
    -0.07
     ধর্ম
    -0.07
     inspected
    -0.07
     قرب
    -0.07
     inspection
    -0.07
    POSITIVE LOGITS
    compet
    0.09
     cognitive
    0.08
     compartments
    0.08
    capacity
    0.08
     capacity
    0.08
     Cognitive
    0.08
     compartment
    0.08
     deficits
    0.08
     capacities
    0.08
    teen
    0.08
    Activations Density 0.004%

    No Known Activations