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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 30613
    Prev
    Next
    INDEX
    Explanations

    acids and bases

    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
    黄金
    -0.08
     Torn
    -0.08
     hurdles
    -0.08
     склады
    -0.08
     이루
    -0.07
     hav
    -0.07
    Coll
    -0.07
     जम्म
    -0.07
     Coll
    -0.07
     gebeurt
    -0.07
    POSITIVE LOGITS
     acidity
    0.11
     aromatic
    0.10
     acidic
    0.10
     donating
    0.09
     promis
    0.09
    acting
    0.09
     nucleus
    0.09
     soluble
    0.09
     freshly
    0.09
    της
    0.09
    Activations Density 0.005%

    No Known Activations