© 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. 11-RESID-POST-AA
    11. 129159
    Prev
    Next
    INDEX
    Explanations

    base

    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
     نس
    -0.09
     vezi
    -0.07
     সদস্য
    -0.07
     Kind
    -0.07
    .Activity
    -0.07
     Members
    -0.07
    տ
    -0.07
     schnellen
    -0.07
    PAIR
    -0.07
     Padres
    -0.07
    POSITIVE LOGITS
     wholehearted
    0.08
    aed
    0.08
    $total
    0.08
     naval
    0.08
     superb
    0.07
    296
    0.07
     cnc
    0.07
    chie
    0.07
     immaculate
    0.07
    %%%%
    0.07
    Activations Density 0.000%

    No Known Activations