© 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. 29301
    Prev
    Next
    INDEX
    Explanations

    me

    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
    ield
    -0.09
     لري
    -0.09
     inder
    -0.08
     meteen
    -0.08
     Kra
    -0.08
     kept
    -0.08
     validade
    -0.08
     breakthrough
    -0.07
     عملي
    -0.07
    'aide
    -0.07
    POSITIVE LOGITS
    -même
    0.10
     mismo
    0.09
    ̂
    0.09
    -mêmes
    0.08
     stesso
    0.08
     chủ
    0.08
    Rab
    0.08
     самого
    0.08
    เอง
    0.08
    hil
    0.08
    Activations Density 0.034%

    No Known Activations