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. 78749
    Prev
    Next
    INDEX
    Explanations

    |

    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
     atuar
    -0.09
    älte
    -0.08
     koj
    -0.08
    كنت
    -0.08
     MACH
    -0.08
    واج
    -0.08
    .ck
    -0.08
     Mellon
    -0.07
    jeti
    -0.07
    <strong
    -0.07
    POSITIVE LOGITS
    0.07
     crois
    0.07
    ிய
    0.07
    ு
    0.07
    tram
    0.07
     sacrific
    0.07
     -*-↵
    0.07
     ngày
    0.07
    217
    0.07
     heaven
    0.07
    Activations Density 0.006%

    No Known Activations