© 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. 54712
    Prev
    Next
    INDEX
    Explanations

    Car manufacturers and parts

    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
    .volume
    -0.07
    Scheme
    -0.07
    scheme
    -0.07
     Prot
    -0.07
    -volume
    -0.07
    _volume
    -0.07
     accent
    -0.07
     deseo
    -0.07
    aties
    -0.06
    -value
    -0.06
    POSITIVE LOGITS
     subcontract
    0.09
     kiba
    0.09
     Kentucky
    0.09
    leister
    0.09
    さん
    0.08
     Haha
    0.08
    Holding
    0.08
    kräfte
    0.08
    ycles
    0.08
     맡
    0.08
    Activations Density 0.024%

    No Known Activations