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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29430
    Prev
    Next
    INDEX
    Explanations

    Narratives

    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
     મૂળ
    -0.08
     newsp
    -0.08
    -pre
    -0.08
    одатель
    -0.08
     eclipse
    -0.08
     मूल
    -0.07
     atrap
    -0.07
     unconstitutional
    -0.07
    "?↵↵
    -0.07
     মূল
    -0.07
    POSITIVE LOGITS
    。然而
    0.10
     hope
    0.09
    。しかし
    0.09
     cheap
    0.09
     hoped
    0.08
     carefree
    0.08
     innoc
    0.08
     tudo
    0.08
     optimism
    0.08
     OK
    0.08
    Activations Density 0.191%

    No Known Activations