© 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. 97750
    Prev
    Next
    INDEX
    Explanations

    м

    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
     проблему
    -0.08
     dhal
    -0.08
     adi
    -0.08
     карту
    -0.08
     ситуацию
    -0.08
     pictured
    -0.08
     opis
    -0.08
    inis
    -0.08
     durée
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    _has
    0.08
    -found
    0.08
    Converters
    0.07
    _router
    0.07
     leakage
    0.07
    king
    0.07
    converter
    0.07
     Leakage
    0.07
    Clin
    0.07
    ound
    0.07
    Activations Density 0.000%

    No Known Activations