Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23272
    Prev
    Next
    INDEX
    Explanations

    chord

    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
     הח
    -0.08
    Sous
    -0.08
    HEMA
    -0.08
     Valenciana
    -0.07
     مصنوع
    -0.07
    /Typography
    -0.07
     Resin
    -0.07
     differently
    -0.07
     powdered
    -0.07
    面对
    -0.07
    POSITIVE LOGITS
    fra
    0.09
     fractions
    0.08
     根
    0.08
     Ко
    0.08
     客
    0.08
    .Speed
    0.08
    	customer
    0.08
    Fra
    0.08
     参数
    0.07
     lengths
    0.07
    Activations Density 0.002%

    No Known Activations