© 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. 11-RESID-POST-AA
    11. 44437
    Prev
    Next
    INDEX
    Explanations

    abuse

    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
     freshness
    -0.08
     QR
    -0.08
     flight
    -0.08
     precision
    -0.08
     kickoff
    -0.07
     qr
    -0.07
     signature
    -0.07
    .sig
    -0.07
     plugged
    -0.07
    soe
    -0.07
    POSITIVE LOGITS
     bullying
    0.19
     harassment
    0.17
    虐
    0.16
     violence
    0.15
     violences
    0.14
     Violence
    0.14
     violência
    0.13
     violencia
    0.13
     abusive
    0.13
     violent
    0.13
    Activations Density 0.069%

    No Known Activations