© 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. 78953
    Prev
    Next
    INDEX
    Explanations

    identical

    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
     beë
    -0.08
     obtained
    -0.08
    hä
    -0.08
     disag
    -0.08
     inverter
    -0.07
    Computed
    -0.07
    onneur
    -0.07
    .tv
    -0.07
    .Interop
    -0.07
    tv
    -0.07
    POSITIVE LOGITS
     anonymity
    0.11
    _plural
    0.08
    _SC
    0.08
    统
    0.08
    anonymous
    0.08
     denominations
    0.08
     sexuales
    0.07
     dough
    0.07
    統
    0.07
    chemas
    0.07
    Activations Density 0.008%

    No Known Activations