© 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. 99538
    Prev
    Next
    INDEX
    Explanations

    subtraction word problems

    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
    nante
    -0.07
    utele
    -0.07
     articul
    -0.07
    umana
    -0.07
    /class
    -0.07
    'ensemble
    -0.07
    nov
    -0.06
    ман
    -0.06
    ാന
    -0.06
    riere
    -0.06
    POSITIVE LOGITS
     বর্তমানে
    0.17
     ప్రస్తుతం
    0.17
     હાલમાં
    0.16
    Currently
    0.16
     ఇప్పటికే
    0.16
     الحالي
    0.16
     Currently
    0.15
    already
    0.15
     momenteel
    0.15
    目前
    0.15
    Activations Density 0.059%

    No Known Activations