© 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. 69432
    Prev
    Next
    INDEX
    Explanations

    Conjunctions and lists

    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
     cuant
    -0.09
     econômico
    -0.09
     econôm
    -0.09
     quantitative
    -0.09
    Quant
    -0.09
     quantit
    -0.09
     Quant
    -0.09
     económico
    -0.08
     quantify
    -0.08
     quantified
    -0.08
    POSITIVE LOGITS
    -security
    0.09
     təhlük
    0.08
     ச
    0.08
     derive
    0.07
    _security
    0.07
    േഴ
    0.07
     shah
    0.07
     censorship
    0.07
     功
    0.07
     zert
    0.07
    Activations Density 0.224%

    No Known Activations