© 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. 11-RESID-POST-AA
    11. 129082
    Prev
    Next
    INDEX
    Explanations

    ation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mystery
    -0.08
    Disposition
    -0.08
     slope
    -0.08
     mert
    -0.08
     kob
    -0.07
     debt
    -0.07
     road
    -0.07
    ica
    -0.07
     val
    -0.07
     guaranteed
    -0.07
    POSITIVE LOGITS
     paused
    0.09
    暂停
    0.09
     pauses
    0.08
    paused
    0.08
    вара
    0.08
    领先
    0.08
     oficiales
    0.08
     ultras
    0.08
     بک
    0.08
     INTERRUPTION
    0.08
    Activations Density 0.001%

    No Known Activations