© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78983
    Prev
    Next
    INDEX
    Explanations

    Capitalization of assets

    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
     આ
    -0.08
     þess
    -0.08
    _aug
    -0.07
     nema
    -0.07
     fountain
    -0.07
     black
    -0.07
     pip
    -0.07
    aked
    -0.07
    付
    -0.07
    ేస
    -0.07
    POSITIVE LOGITS
     représentant
    0.09
    guardar
    0.09
    kanie
    0.09
    aisser
    0.09
    ம்பர்
    0.08
    ocup
    0.08
     représ
    0.08
    .Restr
    0.08
    .keep
    0.08
    joj
    0.08
    Activations Density 0.001%

    No Known Activations