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. 102570
    Prev
    Next
    INDEX
    Explanations

    benefits

    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
    hawk
    -0.09
     наб
    -0.08
     Egg
    -0.08
     hank
    -0.08
    Ny
    -0.08
     menc
    -0.08
     egg
    -0.08
     Ny
    -0.07
    wane
    -0.07
     specimens
    -0.07
    POSITIVE LOGITS
     accru
    0.12
    待遇
    0.09
    ത്തോടെ
    0.08
    -risk
    0.08
    fully
    0.08
     sociaux
    0.08
     общества
    0.08
    措施
    0.07
     ích
    0.07
    seer
    0.07
    Activations Density 0.035%

    No Known Activations