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. 56131
    Prev
    Next
    INDEX
    Explanations

    animal feed

    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
     വിവ
    -0.08
    ambigu
    -0.08
     debounce
    -0.08
     grabbed
    -0.08
     Metadata
    -0.08
    .Metadata
    -0.08
    Changed
    -0.07
     Tango
    -0.07
     Sandra
    -0.07
     Stephen
    -0.07
    POSITIVE LOGITS
    Наз
    0.09
     incess
    0.08
     direcion
    0.08
     ficam
    0.08
     поруч
    0.08
     supervising
    0.08
     niches
    0.08
     لي
    0.08
     nurturing
    0.08
     achievement
    0.08
    Activations Density 0.011%

    No Known Activations