© 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. 103540
    Prev
    Next
    INDEX
    Explanations

    long

    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
     большинстве
    -0.10
     большинства
    -0.09
     toppen
    -0.09
     також
    -0.09
     регулярно
    -0.09
    also
    -0.09
     рекомен
    -0.09
     zahlreichen
    -0.08
     далее
    -0.08
    -year
    -0.08
    POSITIVE LOGITS
     noticing
    0.09
    因
    0.08
    figuration
    0.08
    ference
    0.08
    URLException
    0.08
    ုပ
    0.08
     changing
    0.07
    IPPING
    0.07
    )o
    0.07
    改变
    0.07
    Activations Density 0.001%

    No Known Activations