© 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. 68459
    Prev
    Next
    INDEX
    Explanations

    signal attenuation

    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
     NIL
    -0.09
     cheque
    -0.09
     Wid
    -0.08
    mdat
    -0.08
     Novel
    -0.08
     Beautiful
    -0.08
    (delegate
    -0.08
     миллиард
    -0.08
     BEAUT
    -0.08
    Novel
    -0.08
    POSITIVE LOGITS
     losses
    0.11
     attenuation
    0.11
     incurred
    0.10
    _losses
    0.09
    -loss
    0.09
     loss
    0.09
     pertes
    0.09
     grades
    0.08
     transmission
    0.08
     quantified
    0.08
    Activations Density 0.004%

    No Known Activations