© 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. 75745
    Prev
    Next
    INDEX
    Explanations

    description

    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
     Jog
    -0.08
    Editable
    -0.07
    -0.07
    ुल्क
    -0.07
    ਏ
    -0.07
    htable
    -0.07
    -entry
    -0.07
     JPanel
    -0.07
    篇
    -0.06
    _IB
    -0.06
    POSITIVE LOGITS
     wenigstens
    0.09
    াংশ
    0.08
    assade
    0.08
     mindestens
    0.08
     voller
    0.08
     Kremlin
    0.08
     rgb
    0.08
     некоторых
    0.08
     역시
    0.08
     contrário
    0.08
    Activations Density 0.006%
    No Known Activations