© 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. 79189
    Prev
    Next
    INDEX
    Explanations

    on

    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
    毎
    -0.08
     tending
    -0.08
    oret
    -0.07
     Davies
    -0.07
    264
    -0.07
     pendek
    -0.07
     acuerdo
    -0.07
     cue
    -0.07
     avenue
    -0.07
     By
    -0.07
    POSITIVE LOGITS
     علينا
    0.11
     عليك
    0.11
     impuesto
    0.10
     onto
    0.09
     عليهم
    0.09
     عليكم
    0.09
     preconce
    0.09
     imposed
    0.09
     алдын
    0.08
    Rigid
    0.08
    Activations Density 0.011%

    No Known Activations