© 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. 80
    Prev
    Next
    INDEX
    Explanations

    m, k (math context)

    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
    ces
    -0.09
     Camden
    -0.08
     Helic
    -0.08
     hep
    -0.08
    ુંબ
    -0.08
    _ff
    -0.08
     Globo
    -0.07
     konz
    -0.07
    mes
    -0.07
    ја
    -0.07
    POSITIVE LOGITS
     Syl
    0.07
     sucre
    0.07
     заяв
    0.07
    Claire
    0.07
    ระดับ
    0.07
    nown
    0.07
     scans
    0.07
    宣布
    0.07
    /ex
    0.07
    ryk
    0.07
    Activations Density 0.054%

    No Known Activations