© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95589
    Prev
    Next
    INDEX
    Explanations

    greedy algorithms

    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
     tù
    -0.08
     haɗ
    -0.08
    	enable
    -0.08
     болуы
    -0.08
     Santo
    -0.08
    дах
    -0.07
    ENABLE
    -0.07
     hanga
    -0.07
    سه
    -0.07
    	status
    -0.07
    POSITIVE LOGITS
     greedy
    0.17
     greed
    0.15
     heuristic
    0.13
     heur
    0.12
     decisions
    0.11
     decisiones
    0.10
    gre
    0.10
     rule
    0.10
     blindly
    0.10
    _rule
    0.09
    Activations Density 0.009%

    No Known Activations