© 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. 47390
    Prev
    Next
    INDEX
    Explanations

    time units

    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
     there's
    -0.07
     Awareness
    -0.07
     warga
    -0.07
     awareness
    -0.07
    406
    -0.07
     aware
    -0.07
     motives
    -0.07
    _INLINE
    -0.07
     linking
    -0.07
    the
    -0.07
    POSITIVE LOGITS
    (delay
    0.09
    .Duration
    0.08
     dauern
    0.08
     haste
    0.08
    _seconds
    0.08
     impat
    0.08
     مدد
    0.08
    (rate
    0.08
     waktu
    0.08
     хугаца
    0.08
    Activations Density 0.026%

    No Known Activations