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. 30817
    Prev
    Next
    INDEX
    Explanations

    day

    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
     Debian
    -0.08
     серв
    -0.08
     CPU
    -0.08
    指标
    -0.08
     sheer
    -0.08
     dish
    -0.07
    -0.07
     inode
    -0.07
     físico
    -0.07
     Ubuntu
    -0.07
    POSITIVE LOGITS
     Oral
    0.09
     Mormon
    0.08
     bride
    0.08
    additional
    0.08
    .Stored
    0.08
     धार्मिक
    0.08
     disciples
    0.08
     Noor
    0.08
     repentance
    0.08
     Saints
    0.08
    Activations Density 0.007%

    No Known Activations