© 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. 50627
    Prev
    Next
    INDEX
    Explanations

    Classical music

    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
     Brushes
    -0.09
     strikes
    -0.08
    lany
    -0.08
    _you
    -0.08
    ixels
    -0.08
    _zone
    -0.07
    	flags
    -0.07
     biological
    -0.07
     Horizontal
    -0.07
    	ptr
    -0.07
    POSITIVE LOGITS
     son
    0.11
    Son
    0.09
     Son
    0.09
     Grosso
    0.09
     Konzert
    0.09
     grosses
    0.09
     großes
    0.09
     rond
    0.08
     tern
    0.08
     ದೊಡ್ಡ
    0.08
    Activations Density 0.005%

    No Known Activations