© 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. 25090
    Prev
    Next
    INDEX
    Explanations

    source

    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
    TM
    -0.09
     elites
    -0.08
    Eu
    -0.08
    ==========
    -0.07
    育
    -0.07
    icem
    -0.07
    ic
    -0.07
    λογ
    -0.07
    WR
    -0.07
    om
    -0.07
    POSITIVE LOGITS
     вроде
    0.09
    比如
    0.09
     источ
    0.09
    ächst
    0.08
     হিসাবে
    0.08
     namens
    0.08
     Ita
    0.08
     לד
    0.08
    ателю
    0.08
     quelcon
    0.08
    Activations Density 0.011%

    No Known Activations