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. 23-RESID-POST-AA
    6. 98667
    Prev
    Next
    INDEX
    Explanations

    Iron

    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
     upscale
    -0.09
     assign
    -0.09
    Assign
    -0.08
     adipisicing
    -0.08
     jitter
    -0.08
     rave
    -0.07
    siniz
    -0.07
     uas
    -0.07
     سرگر
    -0.07
     функции
    -0.07
    POSITIVE LOGITS
     filings
    0.15
     oxide
    0.12
     hierro
    0.12
     skillet
    0.12
    ically
    0.12
    нод
    0.11
     ore
    0.11
     deficiency
    0.11
     الحديد
    0.11
    mong
    0.11
    Activations Density 0.011%

    No Known Activations