© 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. 51733
    Prev
    Next
    INDEX
    Explanations

    Helm (Kubernetes package manager)

    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
    ilier
    -0.09
     Console
    -0.08
    Resolved
    -0.08
    _initializer
    -0.07
     रिज
    -0.07
    Hil
    -0.07
    Task
    -0.07
     embarked
    -0.07
     embark
    -0.07
    	Console
    -0.07
    POSITIVE LOGITS
     repo
    0.09
     gum
    0.08
     []*
    0.08
     stable
    0.08
    .repo
    0.08
     nanos
    0.08
     '''↵
    0.08
     fə
    0.08
     stabile
    0.08
    -ли
    0.07
    Activations Density 0.001%

    No Known Activations