© 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. 99767
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    (val
    -0.08
    ுக்க
    -0.08
     emerge
    -0.07
     earned
    -0.07
     emerged
    -0.07
    (rank
    -0.07
     collected
    -0.07
    ுக்
    -0.07
     Nation
    -0.07
     தேசிய
    -0.07
    POSITIVE LOGITS
    ที่จะ
    0.08
     कि
    0.08
    ️
    0.08
     کہ
    0.08
     Rast
    0.07
     అవకాశం
    0.07
     যে
    0.07
     plane
    0.07
     మంది
    0.07
    乌
    0.07
    Activations Density 0.017%

    No Known Activations