© 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. 19-RESID-POST-AA
    11. 19356
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eerie
    -0.08
    ישט
    -0.08
     интерьер
    -0.08
    ערע
    -0.08
    esy
    -0.08
    	queue
    -0.08
     tasteful
    -0.08
     aromas
    -0.08
    :Register
    -0.08
    łos
    -0.08
    POSITIVE LOGITS
     condoms
    0.20
     condom
    0.18
     analsex
    0.17
     contraception
    0.17
     contrace
    0.16
     Condom
    0.15
     safer
    0.14
     protection
    0.14
     Protection
    0.13
     intercourse
    0.13
    Activations Density 0.035%

    No Known Activations