© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 918
    Prev
    Next
    INDEX
    Explanations

    ,re

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Special
    -0.09
     hym
    -0.08
     די
    -0.08
    isty
    -0.08
     కళ
    -0.08
    ↵//↵//
    -0.08
     austr
    -0.08
     Maint
    -0.08
    ifte
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    alek
    0.08
    -priced
    0.08
    994
    0.07
    éré
    0.07
     proyek
    0.07
    152
    0.07
    .discovery
    0.07
    ığın
    0.07
     ah
    0.07
     disorder
    0.07
    Activations Density 0.000%

    No Known Activations