© 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. 68517
    Prev
    Next
    INDEX
    Explanations

    on

    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
     вещества
    -0.08
     substances
    -0.08
    _vocab
    -0.07
     vst
    -0.07
     treasury
    -0.07
    _validator
    -0.07
    αρ
    -0.07
     fear
    -0.07
     Jira
    -0.07
    	set
    -0.07
    POSITIVE LOGITS
     leaned
    0.09
    elerinde
    0.08
     কাট
    0.08
    导演
    0.08
    jejer
    0.08
     habitación
    0.08
     Szene
    0.08
     छोट
    0.08
    厨房
    0.08
     الصغيرة
    0.08
    Activations Density 0.006%

    No Known Activations