© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63847
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    650
    -0.09
     gud
    -0.08
     Nabi
    -0.08
    678
    -0.08
    ത്തു
    -0.07
    238
    -0.07
    .pick
    -0.07
    ning
    -0.07
    649
    -0.07
     när
    -0.07
    POSITIVE LOGITS
     implies
    0.09
     అనే
    0.09
     என்பதை
    0.08
     Noon
    0.08
     minority
    0.08
     ताकि
    0.07
     leads
    0.07
     kugirango
    0.07
    	left
    0.07
    iams
    0.07
    Activations Density 0.076%

    No Known Activations