© 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. 95225
    Prev
    Next
    INDEX
    Explanations

    helmet

    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
    .gs
    -0.07
    gb
    -0.07
    π
    -0.07
     estr
    -0.07
     stark
    -0.07
     primary
    -0.07
     character
    -0.07
    fund
    -0.07
     Pond
    -0.07
    unable
    -0.07
    POSITIVE LOGITS
     suomal
    0.09
    IFICATE
    0.09
     شام
    0.09
     جائز
    0.09
    র্ষ
    0.08
    əlxalq
    0.08
    航
    0.08
     aftermarket
    0.08
    comod
    0.08
     helmets
    0.08
    Activations Density 0.003%

    No Known Activations