© 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. 7-RESID-POST-AA
    11. 844
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     immensely
    -0.08
     gest
    -0.08
     sleeve
    -0.07
     Chelsea
    -0.07
     sleeves
    -0.07
    worthiness
    -0.07
     vit
    -0.07
     discusses
    -0.07
     打
    -0.07
    POSITIVE LOGITS
    Mur
    0.08
    atore
    0.08
    beans
    0.08
     Acr
    0.08
     Mur
    0.07
    uruh
    0.07
     associa
    0.07
    iso
    0.07
    人口
    0.07
     buffalo
    0.07
    Activations Density 0.009%

    No Known Activations