© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18929
    Prev
    Next
    INDEX
    Explanations

    s

    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
    s
    -0.09
    spark
    -0.09
    snow
    -0.09
    SAR
    -0.08
     more
    -0.08
    speech
    -0.08
    e
    -0.08
    social
    -0.08
    েষ্টা
    -0.08
    sar
    -0.08
    POSITIVE LOGITS
    atisf
    0.18
    ufficient
    0.18
    moothing
    0.17
    ynthesis
    0.17
    qrt
    0.16
    utherland
    0.16
    uppress
    0.16
    queeze
    0.16
    ynchronized
    0.15
    ucceed
    0.15
    Activations Density 0.077%

    No Known Activations