© 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. 68684
    Prev
    Next
    INDEX
    Explanations

    manifest

    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
    डक
    -0.08
    মাত্র
    -0.08
     Cre
    -0.08
    courses
    -0.08
    harap
    -0.08
     Jub
    -0.07
    bu
    -0.07
    rot
    -0.07
    upon
    -0.07
    ष्ट
    -0.07
    POSITIVE LOGITS
     Destiny
    0.09
     Voyage
    0.08
     Lys
    0.08
     fo
    0.08
     Arrest
    0.08
    태
    0.08
     destiny
    0.08
    /function
    0.07
     pages
    0.07
     arrest
    0.07
    Activations Density 0.006%

    No Known Activations