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. 77149
    Prev
    Next
    INDEX
    Explanations

    file opening code

    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
     decision
    -0.08
     dự
    -0.08
    ient
    -0.08
    urnal
    -0.08
     निर्णय
    -0.08
    ienti
    -0.07
     upgrade
    -0.07
     ihtiyaç
    -0.07
    ATP
    -0.07
     پام
    -0.07
    POSITIVE LOGITS
    .readlines
    0.10
    уна
    0.09
     totaal
    0.08
     fgets
    0.08
    樓
    0.08
     читать
    0.08
     totale
    0.08
     gelesen
    0.08
    	lines
    0.08
    lines
    0.08
    Activations Density 0.004%

    No Known Activations