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. 42409
    Prev
    Next
    INDEX
    Explanations

    module level

    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
     δεί
    -0.07
    .show
    -0.07
     praça
    -0.07
     auction
    -0.07
     digitale
    -0.07
     ha
    -0.07
     Remedy
    -0.07
     ডিজ
    -0.07
     digitaal
    -0.07
    ha
    -0.07
    POSITIVE LOGITS
     scattered
    0.09
     خارج
    0.08
     flatten
    0.08
    سط
    0.08
    صف
    0.08
    flat
    0.08
     lifts
    0.08
    شل
    0.08
     כח
    0.08
     brows
    0.08
    Activations Density 0.003%

    No Known Activations