© 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. 50790
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
     velocity
    -0.08
    _velocity
    -0.08
    312
    -0.08
     As
    -0.07
    letas
    -0.07
    .As
    -0.07
    velocity
    -0.07
     res
    -0.07
    As
    -0.07
    -0.07
    POSITIVE LOGITS
    772
    0.09
    'au
    0.08
    IDES
    0.08
    azas
    0.08
    (ab
    0.08
     abordar
    0.08
     enctype
    0.08
     organizers
    0.08
     klok
    0.07
    -Ab
    0.07
    Activations Density 0.023%
    No Known Activations