© 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. 112549
    Prev
    Next
    INDEX
    Explanations

    chemical exchanges

    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
    USIC
    -0.07
     தொட
    -0.07
     intellig
    -0.07
    etest
    -0.07
    TX
    -0.07
    ubic
    -0.07
    肖
    -0.07
     persecution
    -0.07
     முய
    -0.07
     குறிப்ப
    -0.07
    POSITIVE LOGITS
     replaces
    0.12
     remplac
    0.12
     replacement
    0.11
     replacements
    0.11
     replaced
    0.11
     replacing
    0.11
     Replacement
    0.11
     remplacement
    0.10
    Replacing
    0.10
    Replacement
    0.10
    Activations Density 0.005%

    No Known Activations