© 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. 113335
    Prev
    Next
    INDEX
    Explanations

    human

    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
    cdf
    -0.08
     pleasures
    -0.08
    cmath
    -0.08
    Yi
    -0.08
     Fahrenheit
    -0.08
     childish
    -0.08
     pleasurable
    -0.08
     oluş
    -0.08
     ingr
    -0.08
    背
    -0.08
    POSITIVE LOGITS
     протест
    0.08
     munt
    0.07
     annotations
    0.07
     fred
    0.07
     neut
    0.07
     toxin
    0.07
     pourrais
    0.07
     IMM
    0.07
     Opportunity
    0.07
     અપ
    0.07
    Activations Density 0.002%

    No Known Activations