© 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 EvalsExportsinterp-engineNEWAPI 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. 110790
    Prev
    Next
    INDEX
    Explanations

    multiply

    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
     confirme
    -0.09
     gezin
    -0.08
    。因此
    -0.08
     confirma
    -0.08
     gameplay
    -0.08
     bestätigt
    -0.08
     предусмотр
    -0.08
    OOL
    -0.08
     theor
    -0.08
     bevestigd
    -0.08
    POSITIVE LOGITS
    (lhs
    0.09
    Synchron
    0.08
    Ich
    0.08
     nimi
    0.07
     lhs
    0.07
     (((
    0.07
     simmer
    0.07
     Buckingham
    0.07
    ich
    0.07
    arios
    0.07
    Activations Density 0.051%

    No Known Activations