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. 58816
    Prev
    Next
    INDEX
    Explanations

    RNA

    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
     উত্ত
    -0.09
    ڀ
    -0.08
    -sp
    -0.08
    ivez
    -0.08
     camisa
    -0.08
     shirt
    -0.07
     divine
    -0.07
     pilgrimage
    -0.07
     vermogen
    -0.07
     واج
    -0.07
    POSITIVE LOGITS
    RNAs
    0.12
    RNA
    0.10
     RNA
    0.10
     regulators
    0.09
     ubiquit
    0.09
    Deletion
    0.09
     regulatory
    0.09
     regulator
    0.09
     ubi
    0.09
     ubiquitous
    0.09
    Activations Density 0.001%

    No Known Activations