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. 15-RESID-POST-AA
    6. 19465
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âte
    -0.09
     Distrito
    -0.08
    aterno
    -0.08
     Cardi
    -0.08
    dated
    -0.08
     sarà
    -0.08
     problemlos
    -0.08
    喜
    -0.07
    todos
    -0.07
    oltre
    -0.07
    POSITIVE LOGITS
     relies
    0.13
     exploiting
    0.13
     consiste
    0.13
     whereby
    0.12
     Essentially
    0.12
     involves
    0.12
     waarbij
    0.12
     leveraging
    0.12
     gumagamit
    0.12
     exploit
    0.11
    Activations Density 0.067%

    No Known Activations