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. 65089
    Prev
    Next
    INDEX
    Explanations

    lengthy texts

    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
    -tier
    -0.08
    )的
    -0.07
    .unwrap
    -0.07
     대한
    -0.07
    .daily
    -0.07
    -0.07
    高
    -0.07
    trash
    -0.07
    管理
    -0.07
    high
    -0.07
    POSITIVE LOGITS
     Receive
    0.09
     Rece
    0.09
     compar
    0.08
    Receive
    0.08
     recevoir
    0.08
     diagnose
    0.08
     behar
    0.08
     overhe
    0.08
     needless
    0.08
     comparator
    0.07
    Activations Density 0.001%

    No Known Activations