© 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. 11-RESID-POST-AA
    11. 70667
    Prev
    Next
    INDEX
    Explanations

    follower

    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
     उद
    -0.08
     cradle
    -0.08
     imposs
    -0.08
    -0.08
     neph
    -0.08
     бес
    -0.08
     σκ
    -0.08
    _STAT
    -0.07
    _ALWAYS
    -0.07
     relieving
    -0.07
    POSITIVE LOGITS
     amassed
    0.09
     opgebouwd
    0.09
    :innen
    0.09
    502
    0.08
    ership
    0.08
     규모
    0.08
     기반
    0.08
    hip
    0.08
     Size
    0.08
     burge
    0.08
    Activations Density 0.018%
    No Known Activations