© 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. 25012
    Prev
    Next
    INDEX
    Explanations

    am

    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
     datas
    -0.08
     löyd
    -0.08
     피부
    -0.08
     Disability
    -0.08
     edm
    -0.08
     trouvé
    -0.08
     صحيح
    -0.07
     gebaseerd
    -0.07
    ');//
    -0.07
     nais
    -0.07
    POSITIVE LOGITS
    fung
    0.08
     ideale
    0.08
    慎
    0.08
    774
    0.07
     czyn
    0.07
    証
    0.07
     selectively
    0.07
     betrachten
    0.07
     лас
    0.07
     идеально
    0.07
    Activations Density 0.000%

    No Known Activations