© 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. 3-RESID-POST-AA
    11. 12883
    Prev
    Next
    INDEX
    Explanations

    might

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pist
    -0.08
     NOM
    -0.08
     sola
    -0.08
     GX
    -0.08
     LU
    -0.08
     gcd
    -0.08
     sg
    -0.08
    Kut
    -0.08
     dine
    -0.08
     Vy
    -0.08
    POSITIVE LOGITS
    partials
    0.08
    Fac
    0.07
     كى
    0.07
    .warn
    0.07
    Interstitial
    0.07
     সন্ধ
    0.07
    组选
    0.07
     రూప
    0.07
    .modify
    0.07
    لع
    0.07
    Activations Density 0.045%

    No Known Activations