© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95333
    Prev
    Next
    INDEX
    Explanations

    Calculating pi

    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
    existent
    -0.09
    突出
    -0.08
     linker
    -0.08
    解绑
    -0.08
    schemas
    -0.07
     secluded
    -0.07
    loading
    -0.07
    绑定
    -0.07
     existência
    -0.07
    果
    -0.07
    POSITIVE LOGITS
     Monte
    0.12
    Monte
    0.12
     tally
    0.11
     simulations
    0.11
     Simulation
    0.11
     simulation
    0.11
     RNG
    0.11
     sampling
    0.10
    Simulation
    0.10
    _sampling
    0.10
    Activations Density 0.004%

    No Known Activations