© 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. 95062
    Prev
    Next
    INDEX
    Explanations

    style

    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
     Bein
    -0.08
    upported
    -0.08
    רס
    -0.08
    initial
    -0.08
     potential
    -0.08
    צר
    -0.08
    मह
    -0.08
    ೂಲ
    -0.07
     solace
    -0.07
    []{"
    -0.07
    POSITIVE LOGITS
    	dst
    0.09
     ost
    0.08
     тебе
    0.08
     gothic
    0.08
     woj
    0.08
    甲
    0.07
     trendy
    0.07
     dst
    0.07
     završ
    0.07
     wux
    0.07
    Activations Density 0.003%

    No Known Activations