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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111765
    Prev
    Next
    INDEX
    Explanations

    Language models

    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
     تعريف
    -0.07
     Montgomery
    -0.07
     cooling
    -0.07
     lunes
    -0.07
     Cool
    -0.07
     Circle
    -0.07
    �
    -0.07
     cool
    -0.07
    .circle
    -0.07
     Mickey
    -0.07
    POSITIVE LOGITS
     trained
    0.11
     NLP
    0.10
     pretrained
    0.10
     halluc
    0.10
    /parser
    0.09
     તાલ
    0.09
     өң
    0.09
     GPT
    0.09
     പരിശീല
    0.08
    /respond
    0.08
    Activations Density 0.018%

    No Known Activations