© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68604
    Prev
    Next
    INDEX
    Explanations

    distributed

    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
    ştır
    -0.07
     grandchildren
    -0.07
    તમ
    -0.07
     સમય
    -0.07
     peri
    -0.07
     meth
    -0.07
     én
    -0.07
    Desp
    -0.07
     propensity
    -0.07
    老人
    -0.07
    POSITIVE LOGITS
    471
    0.08
    712
    0.08
    डल
    0.08
    once
    0.08
    474
    0.08
    Sig
    0.08
    121
    0.08
    บอล
    0.08
    466
    0.07
    -muted
    0.07
    Activations Density 0.000%

    No Known Activations