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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113582
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     "$(
    -0.08
    .Unique
    -0.08
     ਨੂੰ
    -0.07
    ，谢谢
    -0.07
     ECM
    -0.07
     assurances
    -0.07
     innovations
    -0.07
     uniques
    -0.07
     ল
    -0.07
     ইউ
    -0.07
    POSITIVE LOGITS
    Mutable
    0.09
     weighted
    0.08
     Nay
    0.08
    apea
    0.08
    weighted
    0.08
     reachable
    0.08
     Mutable
    0.08
    _FILTER
    0.08
    Paso
    0.08
    орет
    0.08
    Activations Density 0.002%

    No Known Activations