© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91319
    Prev
    Next
    INDEX
    Explanations

    mathematical analysis

    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
     costing
    -0.09
    -0.08
     suitcase
    -0.08
     reconstruction
    -0.08
     costs
    -0.07
     cost
    -0.07
     reduction
    -0.07
    -T
    -0.07
    packing
    -0.07
     '
    -0.07
    POSITIVE LOGITS
     erectile
    0.10
     zaposlen
    0.09
     øvr
    0.09
     peppermint
    0.09
     positif
    0.09
    /operators
    0.08
     außer
    0.08
    Andre
    0.08
     ebb
    0.08
     funcionários
    0.08
    Activations Density 0.066%

    No Known Activations