Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19254
    Prev
    Next
    INDEX
    Explanations

    divisor

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eldo
    -0.09
     timed
    -0.08
    �
    -0.08
    唯
    -0.07
     behalf
    -0.07
    -earth
    -0.07
     yag
    -0.07
    .WR
    -0.07
    earth
    -0.07
    vergoeding
    -0.07
    POSITIVE LOGITS
    Constraints
    0.09
     constraints
    0.09
    igu
    0.08
     prohibits
    0.08
     حدود
    0.08
     thresholds
    0.08
     ensure
    0.08
     Constraints
    0.08
     impose
    0.08
     obviously
    0.07
    Activations Density 0.008%

    No Known Activations