© 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. 16405
    Prev
    Next
    INDEX
    Explanations

    Commas

    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
     касается
    -0.08
     usar
    -0.08
     adicionar
    -0.08
    [out
    -0.08
     günstig
    -0.08
     exigir
    -0.08
     abandonar
    -0.07
     někter
    -0.07
    (Not
    -0.07
     зах
    -0.07
    POSITIVE LOGITS
     בלבד
    0.12
     vielmehr
    0.11
    のみ
    0.10
     suffice
    0.10
     instead
    0.10
     thôi
    0.09
     alone
    0.09
     자체
    0.09
    orca
    0.09
    即可
    0.09
    Activations Density 0.196%

    No Known Activations