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

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 2957
    Prev
    Next
    INDEX
    Explanations

    applicability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funds
    -0.08
    ej
    -0.08
    wel
    -0.07
     eut
    -0.07
     originated
    -0.07
     filmmaking
    -0.07
     credited
    -0.07
     subsid
    -0.07
     husband
    -0.07
     Jenny
    -0.07
    POSITIVE LOGITS
     turístico
    0.08
     bataille
    0.07
     Tire
    0.07
     корист
    0.07
    Orient
    0.07
     Elektr
    0.07
     Delicious
    0.07
     Attack
    0.07
     digestion
    0.07
     данным
    0.07
    Activations Density 0.003%

    No Known Activations