© 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. 78052
    Prev
    Next
    INDEX
    Explanations

    code

    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
    іблі
    -0.08
    point
    -0.08
    /**/*
    -0.08
    /widget
    -0.08
    -tests
    -0.08
    wyddo
    -0.08
    list
    -0.07
    /tests
    -0.07
     tests
    -0.07
    ്വേഷ
    -0.07
    POSITIVE LOGITS
     Palestina
    0.08
    �
    0.07
    entric
    0.07
     väl
    0.07
     pancake
    0.07
     gay
    0.07
    _GRAY
    0.07
    _intro
    0.07
    enzhen
    0.07
     مربوط
    0.07
    Activations Density 0.000%

    No Known Activations