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. 65104
    Prev
    Next
    INDEX
    Explanations

    programming and games

    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
    -0.08
     krachtige
    -0.07
     trendy
    -0.07
    ъти
    -0.07
     accompany
    -0.07
     corte
    -0.07
     compat
    -0.07
     bridging
    -0.07
     thrive
    -0.07
    兼
    -0.07
    POSITIVE LOGITS
     concealed
    0.13
     unbek
    0.12
     conceal
    0.12
     deceptive
    0.12
     скры
    0.12
    隐藏
    0.12
    (hidden
    0.12
    (secret
    0.12
    -hidden
    0.12
     deception
    0.11
    Activations Density 0.005%

    No Known Activations