© 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. 113612
    Prev
    Next
    INDEX
    Explanations

    fruit preparation/description

    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
     silhouette
    -0.08
    ellos
    -0.07
     highest
    -0.07
    _ads
    -0.07
    Ads
    -0.07
     Mend
    -0.07
     portfolio
    -0.07
    Portfolio
    -0.07
     handel
    -0.07
     dopamine
    -0.07
    POSITIVE LOGITS
     בתוך
    0.09
    âtre
    0.09
     الداخل
    0.08
     Inside
    0.08
    /cr
    0.08
    aways
    0.08
     برخه
    0.08
    oha
    0.08
     לפני
    0.08
    ukati
    0.08
    Activations Density 0.004%

    No Known Activations