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. 103392
    Prev
    Next
    INDEX
    Explanations

    himself myself

    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
    Rés
    -0.08
     Masks
    -0.07
    स्क
    -0.07
    SC
    -0.07
     complementary
    -0.07
     Rés
    -0.07
    Tas
    -0.07
    366
    -0.07
     σχολ
    -0.07
     parentes
    -0.07
    POSITIVE LOGITS
     belongings
    0.09
     demeanor
    0.09
     dignity
    0.09
     spont
    0.09
     coragem
    0.09
     courage
    0.08
     volver
    0.08
     vuelva
    0.08
     minced
    0.08
     strength
    0.08
    Activations Density 0.005%

    No Known Activations