© 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. 5467
    Prev
    Next
    INDEX
    Explanations

    ви

    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
    R
    -0.08
    Vk
    -0.07
    m
    -0.07
    S
    -0.07
    .att
    -0.07
    atron
    -0.07
     control
    -0.07
    -app
    -0.07
    Mode
    -0.07
    -control
    -0.07
    POSITIVE LOGITS
    дам
    0.10
    گر
    0.09
     courtyard
    0.09
    িটির
    0.09
    (factory
    0.09
    ie's
    0.08
    (generator
    0.08
    дів
    0.08
    niają
    0.08
    gend
    0.08
    Activations Density 0.000%

    No Known Activations