© 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. 95654
    Prev
    Next
    INDEX
    Explanations

    account activation

    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
    ziemy
    -0.10
     propulsion
    -0.10
     slipper
    -0.08
     motor
    -0.08
     identifica
    -0.08
     QWidget
    -0.08
    дік
    -0.08
     aer
    -0.08
    绑
    -0.08
    طر
    -0.08
    POSITIVE LOGITS
     Cas
    0.08
     Wizards
    0.07
    urken
    0.07
     Deux
    0.07
     Casas
    0.07
    _pref
    0.07
     Out
    0.07
    pref
    0.07
     misunderstood
    0.07
     crime
    0.07
    Activations Density 0.000%

    No Known Activations