© 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. 23-RESID-POST-AA
    11. 48901
    Prev
    Next
    INDEX
    Explanations

    B

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otra
    -0.08
     rico
    -0.08
     فرمان
    -0.08
    оо
    -0.08
     groepen
    -0.07
    ്രമ
    -0.07
    ,:
    -0.07
    askar
    -0.07
     invading
    -0.07
     غور
    -0.07
    POSITIVE LOGITS
    LOCK
    0.08
    IB
    0.08
    IFICATE
    0.08
    lid
    0.07
    DBObject
    0.07
    _connector
    0.07
    寺
    0.07
    IPEDS
    0.07
    TEM
    0.07
    India
    0.07
    Activations Density 0.001%

    No Known Activations