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. 113812
    Prev
    Next
    INDEX
    Explanations

    variable rate

    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
    isol
    -0.08
     isolated
    -0.08
     isol
    -0.08
     Genetics
    -0.07
     izol
    -0.07
     lonely
    -0.07
     orchestr
    -0.07
    іг
    -0.07
     improbable
    -0.07
     Coorden
    -0.07
    POSITIVE LOGITS
     fluctu
    0.12
     fluctuate
    0.11
    额度
    0.10
     unpredict
    0.10
     unpredictable
    0.10
     रहेगा
    0.09
     fluctuations
    0.09
     fluct
    0.09
    变化
    0.09
     राशि
    0.08
    Activations Density 0.008%

    No Known Activations