© 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. 18702
    Prev
    Next
    INDEX
    Explanations

    999 or 000

    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
     needle
    -0.07
    egro
    -0.07
    upy
    -0.07
    hyw
    -0.07
     setting
    -0.07
     hake
    -0.07
     houd
    -0.07
     وظيفة
    -0.07
     houdt
    -0.07
    modify
    -0.07
    POSITIVE LOGITS
    000
    0.15
    oooooooo
    0.11
    727
    0.10
    aaaaaaaa
    0.10
    ffffffff
    0.10
    038
    0.10
    029
    0.10
    017
    0.10
    ۰۰
    0.10
    oooo
    0.09
    Activations Density 0.006%

    No Known Activations