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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 598
    Prev
    Next
    INDEX
    Explanations

    classification

    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
     unc
    -0.09
     Sirius
    -0.08
    Sources
    -0.08
     дома
    -0.08
     uninterrupted
    -0.07
    amm
    -0.07
    ources
    -0.07
    Vir
    -0.07
     Pir
    -0.07
     figures
    -0.07
    POSITIVE LOGITS
    表示
    0.08
     produit
    0.08
    র্শ
    0.08
    र्शन
    0.08
    診
    0.08
    认为
    0.08
    诊
    0.08
     પ્રય
    0.07
    বাদ
    0.07
    sa
    0.07
    Activations Density 0.009%

    No Known Activations