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. 56232
    Prev
    Next
    INDEX
    Explanations

    ordered

    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
    athing
    -0.08
     latency
    -0.07
    忙
    -0.07
    idle
    -0.07
    aths
    -0.07
    cmd
    -0.07
    enci
    -0.07
     காண
    -0.07
     ide
    -0.07
     Kaiser
    -0.07
    POSITIVE LOGITS
     counterpart
    0.09
     pairs
    0.09
     distint
    0.08
     stacks
    0.08
     rectangular
    0.08
     tuples
    0.08
     uv
    0.08
     quadrant
    0.08
     permutations
    0.08
    Pairs
    0.08
    Activations Density 0.006%

    No Known Activations