© 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. 45579
    Prev
    Next
    INDEX
    Explanations

    code and language

    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
     Watt
    -0.09
    _income
    -0.08
     slider
    -0.08
     revenus
    -0.08
     sier
    -0.07
     endocrine
    -0.07
    .slider
    -0.07
     SQL
    -0.07
     Survivor
    -0.07
     Taxes
    -0.07
    POSITIVE LOGITS
    da
    0.08
    -da
    0.08
    drž
    0.08
     hakim
    0.08
     hökm
    0.08
    lif
    0.08
    هاب
    0.08
     possesses
    0.07
    ta
    0.07
    0.07
    Activations Density 0.000%
    No Known Activations