© 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. 3-RESID-POST-AA
    11. 2982
    Prev
    Next
    INDEX
    Explanations

    ant

    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
    achelorette
    -0.09
    beitet
    -0.09
    _proto
    -0.09
    泊
    -0.08
     arrog
    -0.08
    */
↵
↵
    -0.08
    intro
    -0.08
    ritu
    -0.08
     настав
    -0.08
    ritur
    -0.08
    POSITIVE LOGITS
     style
    0.08
     difference
    0.08
     parc
    0.07
    0.07
    	style
    0.07
     insp
    0.07
    ريك
    0.07
    (style
    0.07
     fund
    0.07
     HAV
    0.07
    Activations Density 0.000%
    No Known Activations