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

    Neuronpedia

    Jacobian LensNEW
    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. 68913
    Prev
    Next
    INDEX
    Explanations

    Sync

    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
    Contest
    -0.08
    Indicator
    -0.08
     ಪಾತ್ರ
    -0.08
    clip
    -0.07
    herence
    -0.07
    角色
    -0.07
    bone
    -0.07
    Role
    -0.07
     ghost
    -0.07
    ghost
    -0.07
    POSITIVE LOGITS
    enean
    0.09
    静
    0.09
     Fre
    0.08
    enea
    0.08
     qual
    0.08
    enez
    0.08
     Fa
    0.07
     तत्काल
    0.07
    ene
    0.07
    フ
    0.07
    Activations Density 0.003%

    No Known Activations