© 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. 5755
    Prev
    Next
    INDEX
    Explanations

    исп

    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
    stwo
    -0.08
    ството
    -0.08
    ENCY
    -0.08
    Sight
    -0.08
    ство
    -0.08
    gerecht
    -0.07
     Sight
    -0.07
    hető
    -0.07
     específicamente
    -0.07
     coup
    -0.07
    POSITIVE LOGITS
    олня
    0.21
    ольз
    0.14
    олнение
    0.13
    роб
    0.12
    олнитель
    0.12
    ытай
    0.12
    ыты
    0.11
    рав
    0.11
    олн
    0.10
    or
    0.10
    Activations Density 0.002%

    No Known Activations