© 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. 573
    Prev
    Next
    INDEX
    Explanations

    cybersecurity

    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
     reunion
    -0.10
    歌曲
    -0.10
     Messi
    -0.10
     Cheer
    -0.10
     admirer
    -0.09
     partidos
    -0.09
     billi
    -0.09
     vowel
    -0.09
     Künstler
    -0.09
     Zuschauer
    -0.09
    POSITIVE LOGITS
     cybersecurity
    0.17
     security
    0.17
     beveilig
    0.16
    Security
    0.16
     सुरक्षा
    0.16
     Security
    0.16
     امنیت
    0.16
    security
    0.15
     സുരക്ഷ
    0.15
    /security
    0.15
    Activations Density 0.132%

    No Known Activations