© 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. 65606
    Prev
    Next
    INDEX
    Explanations

    significance level

    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
    eiende
    -0.08
     भीतर
    -0.08
     bureau
    -0.08
    سنگ
    -0.08
     오는
    -0.08
    حاد
    -0.08
     سقوط
    -0.07
    बा
    -0.07
    לא
    -0.07
    או
    -0.07
    POSITIVE LOGITS
     Victor
    0.09
     Duke
    0.09
     �
    0.08
     vif
    0.08
     stm
    0.07
     intervent
    0.07
     Jerry
    0.07
     echar
    0.07
    Victor
    0.07
     pec
    0.07
    Activations Density 0.002%

    No Known Activations