© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    Integration and incorporation

    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
     travels
    -0.07
     اصلی
    -0.07
    veil
    -0.07
    ствие
    -0.07
     predicament
    -0.07
     Loves
    -0.07
    (Paths
    -0.07
     Proxy
    -0.07
    /C
    -0.07
     پاک
    -0.07
    POSITIVE LOGITS
    纳
    0.10
    into
    0.10
    _into
    0.10
     woven
    0.09
     vào
    0.09
    Into
    0.09
     into
    0.09
    .into
    0.08
    进去
    0.08
     встро
    0.08
    Activations Density 0.042%

    No Known Activations