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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98602
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sender
    -0.08
     mascot
    -0.08
     President
    -0.08
     Facilit
    -0.07
     bruker
    -0.07
    .python
    -0.07
    .sender
    -0.07
     Vert
    -0.07
     Versa
    -0.07
     excesso
    -0.07
    POSITIVE LOGITS
     стер
    0.08
     suction
    0.08
    Awesome
    0.07
     натураль
    0.07
     XHTML
    0.07
    ిస్ట
    0.07
     brindar
    0.07
    ార్
    0.07
     обрат
    0.07
     })}↵
    0.07
    Activations Density 0.001%

    No Known Activations