© 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. 91254
    Prev
    Next
    INDEX
    Explanations

    sayings

    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
     ओकर
    -0.09
     تعرض
    -0.08
     constate
    -0.08
    inetic
    -0.08
     علت
    -0.08
     الإصابة
    -0.08
     سرطان
    -0.08
     Constitucional
    -0.08
     واج
    -0.07
     يقوم
    -0.07
    POSITIVE LOGITS
     motto
    0.12
     aptly
    0.10
    理念
    0.10
     Motto
    0.10
     mantra
    0.10
     slogan
    0.10
     principles
    0.10
     dictum
    0.09
     sayings
    0.09
     lautet
    0.09
    Activations Density 0.110%

    No Known Activations