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. 111643
    Prev
    Next
    INDEX
    Explanations

    inspirational, positive affirmations

    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
    Forbidden
    -0.09
     joking
    -0.08
     арналған
    -0.08
    禁止
    -0.08
     verboden
    -0.08
     기사
    -0.08
     اسلام
    -0.07
    TXT
    -0.07
     impér
    -0.07
    は禁止
    -0.07
    POSITIVE LOGITS
     сможете
    0.10
     healthier
    0.10
     chances
    0.09
     podremos
    0.09
     eficacia
    0.09
     મળશે
    0.09
     melhora
    0.09
     chance
    0.09
     быстрее
    0.09
    ാകും
    0.09
    Activations Density 0.189%

    No Known Activations