© 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. 19-RESID-POST-AA
    11. 103587
    Prev
    Next
    INDEX
    Explanations

    Organisms

    np_max-act-logits · gemini-2.0-flash
    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
     disability
    -0.10
     тез
    -0.09
     Disability
    -0.08
    spoken
    -0.08
     Visit
    -0.08
     disabilities
    -0.08
     visit
    -0.08
     Visiting
    -0.07
     נס
    -0.07
     painful
    -0.07
    POSITIVE LOGITS
     organisms
    0.15
     организм
    0.14
     organismos
    0.14
     organism
    0.13
     organismes
    0.12
     النباتات
    0.11
     processes
    0.11
     Prozesse
    0.11
     organismo
    0.11
     organisme
    0.11
    Activations Density 0.009%

    No Known Activations