Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99102
    Prev
    Next
    INDEX
    Explanations

    immediately

    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
    ump
    -0.08
     Longitude
    -0.07
    ắn
    -0.07
    longitude
    -0.07
    .uml
    -0.07
    ковод
    -0.07
     Prü
    -0.07
    Tra
    -0.07
     SOP
    -0.07
    Led
    -0.07
    POSITIVE LOGITS
    aneously
    0.11
     തന്നെ
    0.10
     থেকেই
    0.10
     लगे
    0.09
    ทัน
    0.09
     तुरंत
    0.09
    iatamente
    0.09
    以来
    0.08
     saja
    0.08
     gratification
    0.08
    Activations Density 0.018%

    No Known Activations