© 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. 113698
    Prev
    Next
    INDEX
    Explanations

    Adult comedy prompts

    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
    elah
    -0.08
    硕
    -0.08
     gair
    -0.08
     vital
    -0.08
     snabb
    -0.08
     铭
    -0.08
     التاس
    -0.08
     zawod
    -0.08
     Mən
    -0.08
     negen
    -0.08
    POSITIVE LOGITS
     dysfunctional
    0.09
     Pav
    0.09
    075
    0.08
     skeptical
    0.08
     необы
    0.08
     skept
    0.08
     Checker
    0.08
     weird
    0.07
     absurd
    0.07
     entdecken
    0.07
    Activations Density 0.003%

    No Known Activations