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. 97081
    Prev
    Next
    INDEX
    Explanations

    Transportation hubs

    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
    rolle
    -0.08
     Insta
    -0.08
     besonderes
    -0.08
    ulka
    -0.08
     }];↵
    -0.08
     компани
    -0.07
     }]
    -0.07
     hype
    -0.07
     markup
    -0.07
     известно
    -0.07
    POSITIVE LOGITS
     Liverpool
    0.09
     Michigan
    0.09
     Zool
    0.09
     terminé
    0.08
     termini
    0.08
     Nation
    0.08
    Canada
    0.08
    File
    0.08
     Haupt
    0.08
    Gl
    0.08
    Activations Density 0.004%

    No Known Activations