© 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. 23-RESID-POST-AA
    11. 47857
    Prev
    Next
    INDEX
    Explanations

    Song/album titles

    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
     Ml
    -0.09
     Spa
    -0.08
     Carol
    -0.08
     Ski
    -0.08
     Helm
    -0.07
    Spa
    -0.07
    패
    -0.07
    림
    -0.07
     smith
    -0.07
     ko
    -0.07
    POSITIVE LOGITS
    0.08
    Probe
    0.08
    Array
    0.08
     probes
    0.08
     freezing
    0.07
    299
    0.07
    probe
    0.07
     abnormalities
    0.07
     Platforms
    0.07
     unacceptable
    0.07
    Activations Density 0.001%
    No Known Activations