© 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. 3-RESID-POST-AA
    11. 3002
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     machinery
    -0.09
     cast
    -0.08
     pomp
    -0.08
    ร
    -0.07
     bracket
    -0.07
     framed
    -0.07
     superficial
    -0.07
     equ
    -0.07
    _CAST
    -0.07
     casting
    -0.07
    POSITIVE LOGITS
     Memories
    0.09
    hydr
    0.09
     zumindest
    0.09
    세요
    0.08
     Sar
    0.08
     medi
    0.08
     Medi
    0.08
     Möglichkeiten
    0.08
     chinese
    0.08
     mediator
    0.08
    Activations Density 0.030%

    No Known Activations