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. 11-RESID-POST-AA
    6. 30524
    Prev
    Next
    INDEX
    Explanations

    Something comes to mind

    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
     overst
    -0.08
    atement
    -0.07
    Bug
    -0.07
     chang
    -0.07
    Twe
    -0.07
    .export
    -0.07
     suicide
    -0.07
     starving
    -0.07
     rape
    -0.07
     slechte
    -0.07
    POSITIVE LOGITS
     evokes
    0.12
    想到
    0.11
     évo
    0.11
     asociado
    0.10
     imediatamente
    0.09
     associado
    0.09
     evoke
    0.09
     invokes
    0.09
     immediately
    0.09
     imagery
    0.09
    Activations Density 0.038%

    No Known Activations