© 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. 25866
    Prev
    Next
    INDEX
    Explanations

    systematic sampling

    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
     spent
    -0.08
     dialog
    -0.08
    .dialog
    -0.08
    	dialog
    -0.07
     спор
    -0.07
     republic
    -0.07
    .scene
    -0.07
     dock
    -0.07
     Dubrov
    -0.07
     مکمل
    -0.07
    POSITIVE LOGITS
     sieve
    0.09
     deterministic
    0.09
     sweeping
    0.09
     indexing
    0.09
     방식
    0.09
    Periodic
    0.08
     periodic
    0.08
    选号
    0.08
    _PATTERN
    0.08
     नम्बर
    0.08
    Activations Density 0.008%

    No Known Activations