© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47876
    Prev
    Next
    INDEX
    Explanations

    Пер

    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
     emp
    -0.08
     piles
    -0.07
     聚
    -0.07
     fällt
    -0.07
     sob
    -0.07
     revolt
    -0.07
     polov
    -0.07
     unpopular
    -0.07
    _VISIBLE
    -0.07
     asesin
    -0.07
    POSITIVE LOGITS
    ех
    0.10
     router
    0.08
    ENC
    0.08
    ამის
    0.08
    prav
    0.08
    DIR
    0.08
     Router
    0.08
    router
    0.08
     redirects
    0.08
     Redwood
    0.08
    Activations Density 0.001%

    No Known Activations