© 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 EvalsExportsinterp-engineNEWAPI 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. 70238
    Prev
    Next
    INDEX
    Explanations

    Profanity

    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
    优惠
    -0.10
     parall
    -0.09
     할인
    -0.09
    Customizer
    -0.08
    Parallel
    -0.08
    _parallel
    -0.08
     watercolor
    -0.08
     Prix
    -0.08
    担当
    -0.08
     العم
    -0.08
    POSITIVE LOGITS
     profanity
    0.16
     obscene
    0.13
     insults
    0.12
     angry
    0.12
     anger
    0.11
     masturb
    0.11
     hateful
    0.11
     suicidal
    0.11
     insulting
    0.11
     сексу
    0.11
    Activations Density 0.020%

    No Known Activations