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. 42335
    Prev
    Next
    INDEX
    Explanations

    equal

    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
     ty
    -0.08
     TAG
    -0.08
     retreats
    -0.07
     closures
    -0.07
    äten
    -0.07
     retreat
    -0.07
     confirmations
    -0.07
     cigar
    -0.07
     पक्ष
    -0.07
    TAG
    -0.07
    POSITIVE LOGITS
     개선
    0.09
    Improve
    0.09
     improvement
    0.08
     forbed
    0.08
     Improve
    0.08
     સુધ
    0.08
    Benefits
    0.08
     الجلد
    0.08
     Benefits
    0.08
     improve
    0.08
    Activations Density 0.001%

    No Known Activations