© 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. 19-RESID-POST-AA
    11. 103307
    Prev
    Next
    INDEX
    Explanations

    sil

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    metr
    -0.09
    lerden
    -0.08
    重
    -0.08
    izable
    -0.08
    adoù
    -0.08
    omat
    -0.08
     liberated
    -0.08
    idia
    -0.07
    azada
    -0.07
    കരണ
    -0.07
    POSITIVE LOGITS
     силу
    0.10
    	use
    0.09
    houette
    0.08
     сцен
    0.08
     silhouette
    0.08
     suhte
    0.08
     trenut
    0.08
    hh
    0.08
    0.08
     selectie
    0.08
    Activations Density 0.002%
    No Known Activations