© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110336
    Prev
    Next
    INDEX
    Explanations

    recipes

    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
    ൂർ
    -0.09
     valign
    -0.08
    urna
    -0.08
    ൂര്
    -0.08
     fj
    -0.08
     Auction
    -0.08
    unto
    -0.08
     上传
    -0.08
     Severe
    -0.07
    Zh
    -0.07
    POSITIVE LOGITS
    Aantal
    0.09
     इच्छ
    0.09
     interpersonal
    0.09
    人数
    0.08
     मात्रा
    0.08
     рассчит
    0.08
     ನಿಮ
    0.08
     அள
    0.08
     duplic
    0.08
    规模
    0.08
    Activations Density 0.044%

    No Known Activations