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. 53429
    Prev
    Next
    INDEX
    Explanations

    and

    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
    (act
    -0.08
     Forg
    -0.08
     Peng
    -0.07
     möchte
    -0.07
     Dessa
    -0.07
     jubile
    -0.07
     Absch
    -0.07
    Toda
    -0.07
     Peg
    -0.07
     Сер
    -0.07
    POSITIVE LOGITS
     society
    0.08
     psyche
    0.08
     \'
    0.07
     academia
    0.07
     teens
    0.07
     üzer
    0.07
     alentours
    0.07
     environs
    0.07
     escritório
    0.07
     secours
    0.07
    Activations Density 0.200%

    No Known Activations