© 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. 50679
    Prev
    Next
    INDEX
    Explanations

    numbers around 080

    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
    908
    -0.10
    88
    -0.09
    алап
    -0.09
    706
    -0.08
     huet
    -0.08
    728
    -0.08
    881
    -0.08
    904
    -0.08
     restera
    -0.08
    708
    -0.08
    POSITIVE LOGITS
    079
    0.14
    080
    0.13
    08
    0.12
    081
    0.11
    078
    0.11
    077
    0.10
    083
    0.10
    082
    0.09
    007
    0.09
    008
    0.09
    Activations Density 0.021%

    No Known Activations