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. 112280
    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
     Sparta
    -0.07
     formal
    -0.07
     prima
    -0.07
    ienst
    -0.07
     tanti
    -0.07
     cielo
    -0.07
     Indeed
    -0.07
    73
    -0.07
     executive
    -0.07
    Indeed
    -0.06
    POSITIVE LOGITS
    ITS
    0.08
    贷
    0.08
     suck
    0.08
     tats
    0.08
    还能
    0.08
    卢
    0.08
     absch
    0.07
    ITED
    0.07
    okot
    0.07
    ાષ્ટ્ર
    0.07
    Activations Density 0.142%

    No Known Activations