© 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. 23-RESID-POST-AA
    11. 50687
    Prev
    Next
    INDEX
    Explanations

    .

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trondheim
    -0.10
    utsit
    -0.10
     minuut
    -0.10
    স্পত
    -0.10
     sprint
    -0.10
    tritur
    -0.09
    Sprint
    -0.09
    isciplin
    -0.09
     kip
    -0.09
     Kip
    -0.09
    POSITIVE LOGITS
    285
    0.24
    286
    0.16
     CDA
    0.14
    284
    0.13
     cea
    0.13
     Chelsea
    0.12
    28
    0.10
     CBD
    0.10
    CEA
    0.10
     CAD
    0.10
    Activations Density 0.006%

    No Known Activations