© 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. 15-RESID-POST-AA
    11. 16298
    Prev
    Next
    INDEX
    Explanations

    Remote connections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     यांनी
    -0.08
    unami
    -0.08
     woman
    -0.07
     Nun
    -0.07
    -inflammatory
    -0.07
    EEDED
    -0.07
     giải
    -0.07
     Minor
    -0.07
     Cs
    -0.07
    ơn
    -0.07
    POSITIVE LOGITS
     remotely
    0.11
     чуж
    0.11
     inaccessible
    0.11
     remoto
    0.10
     remote
    0.10
     diretamente
    0.10
     напрямую
    0.10
    Remote
    0.09
     existentes
    0.09
     remot
    0.09
    Activations Density 0.028%

    No Known Activations