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. 60687
    Prev
    Next
    INDEX
    Explanations

    ened

    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
    653
    -0.09
    593
    -0.08
     franch
    -0.08
    攝
    -0.08
    影院
    -0.08
    _CREAT
    -0.08
     crews
    -0.07
    .Asset
    -0.07
    373
    -0.07
     Odd
    -0.07
    POSITIVE LOGITS
    prefer
    0.09
     preferably
    0.09
     tercih
    0.08
     kahle
    0.08
     pauvre
    0.08
     prefix
    0.07
     edilmiş
    0.07
     welche
    0.07
     какая
    0.07
     какие
    0.07
    Activations Density 0.005%

    No Known Activations