© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 64109
    Prev
    Next
    INDEX
    Explanations

    Frying

    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
     slack
    -0.09
     Slack
    -0.08
    spel
    -0.08
    ®
    -0.08
    Slack
    -0.08
    %!
    -0.08
     '!
    -0.08
     Conversation
    -0.08
     Thing
    -0.08
     Convers
    -0.08
    POSITIVE LOGITS
     атак
    0.09
     എണ്ണ
    0.09
     Flood
    0.09
     тым
    0.08
     сто
    0.08
     examin
    0.08
    ="//
    0.08
     plated
    0.08
     غسل
    0.07
     كمية
    0.07
    Activations Density 0.013%

    No Known Activations