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. 61043
    Prev
    Next
    INDEX
    Explanations

    geometric arrangements

    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
     பாட
    -0.09
    lyrics
    -0.08
     قوم
    -0.08
     مخت
    -0.08
     مف
    -0.08
    leng
    -0.08
     ngaj
    -0.08
    .ide
    -0.08
    reviews
    -0.07
     endorsement
    -0.07
    POSITIVE LOGITS
     compartments
    0.10
     oluş
    0.09
     Regions
    0.09
     ontstaan
    0.09
     entstehen
    0.08
     quatro
    0.08
     zählt
    0.08
     panes
    0.08
     Tiles
    0.08
     Counting
    0.08
    Activations Density 0.020%

    No Known Activations