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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 90215
    Prev
    Next
    INDEX
    Explanations

    email

    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
     cogn
    -0.09
    ઝ
    -0.08
     uno
    -0.07
    -Mit
    -0.07
     vez
    -0.07
     Worst
    -0.07
    认识
    -0.07
    zir
    -0.07
    lse
    -0.07
    -Gr
    -0.07
    POSITIVE LOGITS
     lokaci
    0.08
     אלה
    0.08
     ordeal
    0.08
     laman
    0.08
     насел
    0.08
     아
    0.08
     arall
    0.07
    оку
    0.07
    짓
    0.07
     éta
    0.07
    Activations Density 0.020%

    No Known Activations