Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87843
    Prev
    Next
    INDEX
    Explanations

    secure communications

    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
    ldə
    -0.09
     palp
    -0.09
    lun
    -0.09
     pata
    -0.08
    ייחס
    -0.08
     Ogun
    -0.08
     arreg
    -0.08
    луш
    -0.08
     কমিশ
    -0.08
     Lions
    -0.08
    POSITIVE LOGITS
     encrypted
    0.14
     privacy
    0.13
    Encrypted
    0.13
     സുരക്ഷ
    0.13
     encryption
    0.12
     privacidad
    0.12
    Encryption
    0.12
     stealth
    0.12
    Privacy
    0.12
     સુર
    0.12
    Activations Density 0.028%

    No Known Activations