© 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. 11-RESID-POST-AA
    11. 30178
    Prev
    Next
    INDEX
    Explanations

    1

    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
    auts
    -0.08
     نفسها
    -0.08
     anhand
    -0.08
    ↵                ↵
    -0.08
     :)
    -0.07
     whatever
    -0.07
    效率
    -0.07
    _aut
    -0.07
     autoc
    -0.07
    yay
    -0.07
    POSITIVE LOGITS
     банка
    0.09
     disclaim
    0.09
     bagu
    0.09
     tbsp
    0.09
     упаков
    0.09
     adet
    0.09
     lampe
    0.08
     гру
    0.08
     secluded
    0.08
     rq
    0.08
    Activations Density 0.017%

    No Known Activations