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. 46486
    Prev
    Next
    INDEX
    Explanations

    in

    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
     effectivement
    -0.08
    aumont
    -0.08
    _wrapper
    -0.07
     darse
    -0.07
     maladie
    -0.07
     inte
    -0.07
    enson
    -0.07
     sette
    -0.07
     realize
    -0.07
    ene
    -0.07
    POSITIVE LOGITS
     smelling
    0.10
     aroma
    0.09
     аромат
    0.09
     smelled
    0.09
     scent
    0.09
     aromas
    0.09
     smell
    0.09
    textures
    0.09
    -muted
    0.08
    _BUFFER
    0.08
    Activations Density 0.003%

    No Known Activations