© 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. 44635
    Prev
    Next
    INDEX
    Explanations

    analyses

    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
     Orthodox
    -0.08
    Worldwide
    -0.08
     honor
    -0.08
     Victoria
    -0.08
     honorable
    -0.07
    Len
    -0.07
     सल
    -0.07
    融合
    -0.07
     comer
    -0.07
     award
    -0.07
    POSITIVE LOGITS
     sensitivity
    0.17
    Sensitivity
    0.16
     sensitiv
    0.15
     Sens
    0.14
     sensibilidad
    0.14
     sensit
    0.13
     sensitive
    0.13
     संव
    0.12
    敏
    0.12
     حساس
    0.12
    Activations Density 0.010%

    No Known Activations