© 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. 95465
    Prev
    Next
    INDEX
    Explanations

    depreciation

    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
    ovani
    -0.08
    fü
    -0.08
    VS
    -0.07
    kü
    -0.07
     integrated
    -0.07
    anen
    -0.07
    oph
    -0.07
     모
    -0.07
     Bö
    -0.07
     Bunny
    -0.07
    POSITIVE LOGITS
     disgrace
    0.09
    _HISTORY
    0.09
     ঘোষণা
    0.09
    _OCCURRED
    0.08
    olicy
    0.08
     عملي
    0.08
    හ
    0.08
     ঘোষ
    0.08
    _history
    0.08
    /current
    0.07
    Activations Density 0.002%

    No Known Activations