© 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. 15-RESID-POST-AA
    6. 16285
    Prev
    Next
    INDEX
    Explanations

    Versions of "to be"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     позволит
    -0.09
     donnera
    -0.08
    ాలతో
    -0.08
    ಗಳಿಂದ
    -0.08
    ರಿಂದ
    -0.07
     bedeutet
    -0.07
     permettra
    -0.07
    」,
    -0.07
     permitirá
    -0.07
    ులతో
    -0.07
    POSITIVE LOGITS
     быть
    0.15
     είναι
    0.15
     является
    0.15
     essere
    0.15
     is
    0.15
     являются
    0.15
     being
    0.15
     être
    0.14
    是一
    0.14
     være
    0.14
    Activations Density 0.160%

    No Known Activations