© 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. 19-RESID-POST-AA
    11. 103199
    Prev
    Next
    INDEX
    Explanations

    a

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|reserved_200014|>
    -0.09
    olics
    -0.08
    ários
    -0.08
    arios
    -0.08
    ujących
    -0.08
     hrs
    -0.08
    Now
    -0.08
     diverses
    -0.08
    <|reserved_200009|>
    -0.08
    -semibold
    -0.08
    POSITIVE LOGITS
     object's
    0.12
     item's
    0.11
     Eğer
    0.10
     person's
    0.10
     is
    0.10
     property's
    0.10
    人在
    0.09
     state's
    0.09
     যদি
    0.09
     truly
    0.09
    Activations Density 0.022%

    No Known Activations