© 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. 113137
    Prev
    Next
    INDEX
    Explanations

    for

    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
    resa
    -0.08
     अभिय
    -0.08
    /en
    -0.08
    ুভ
    -0.08
     behandeld
    -0.08
    pared
    -0.08
     endemic
    -0.08
    /sc
    -0.08
     প্রতি
    -0.07
    tores
    -0.07
    POSITIVE LOGITS
    ício
    0.07
    ák
    0.07
     semillas
    0.07
     lead
    0.07
    ictionaries
    0.07
     لمدة
    0.07
     chví
    0.07
     fearless
    0.07
    cision
    0.07
     शब्द
    0.07
    Activations Density 0.001%

    No Known Activations