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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48519
    Prev
    Next
    INDEX
    Explanations

    say "ader"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     éditions
    -0.09
    inyin
    -0.08
     guessing
    -0.08
     Smartphone
    -0.08
    区
    -0.08
     인터넷
    -0.08
     Spect
    -0.08
     Scene
    -0.08
     Chiang
    -0.07
    _CLIENT
    -0.07
    POSITIVE LOGITS
    quant
    0.10
     quant
    0.10
     ಬ್ಯ
    0.10
    Quant
    0.09
    	back
    0.09
     quantify
    0.09
     cuant
    0.09
    -al
    0.09
    _back
    0.09
     ಪ
    0.09
    Activations Density 0.006%

    No Known Activations