© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6065
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .sep
    -0.08
     살
    -0.08
    나라
    -0.08
    .country
    -0.08
     satisfaction
    -0.08
     Satisfaction
    -0.08
     завед
    -0.08
     나라
    -0.08
    满意
    -0.08
    견
    -0.08
    POSITIVE LOGITS
    16
    0.30
    32
    0.30
    64
    0.27
    128
    0.27
    256
    0.26
    ১৬
    0.26
    १६
    0.25
    512
    0.24
     sixteen
    0.23
    １６
    0.22
    Activations Density 0.390%

    No Known Activations