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. 8392
    Prev
    Next
    INDEX
    Explanations

    Software development tools/libraries

    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
    тва
    -0.08
    せ
    -0.08
     subsidi
    -0.07
    Inclus
    -0.07
     nghĩa
    -0.07
     Sono
    -0.07
    :nth
    -0.07
     Vale
    -0.07
     ...,
    -0.07
    いた
    -0.07
    POSITIVE LOGITS
     제대로
    0.09
     properly
    0.09
     설치
    0.09
     pops
    0.08
     megfelelő
    0.08
     pop
    0.08
     reliably
    0.08
     installé
    0.08
     હાથ
    0.08
     ache
    0.08
    Activations Density 0.033%

    No Known Activations