© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95405
    Prev
    Next
    INDEX
    Explanations

    punctuation, delimiters

    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
     att
    -0.09
    ोलन
    -0.07
    -stop
    -0.07
     студентов
    -0.07
    ,:,
    -0.07
     અટ
    -0.07
     nq
    -0.07
    统
    -0.07
     начале
    -0.07
     специалистов
    -0.07
    POSITIVE LOGITS
    مل
    0.08
    accio
    0.08
    lava
    0.07
    remaining
    0.07
    Cit
    0.07
    acc
    0.07
    مال
    0.07
    empi
    0.07
    xml
    0.07
    htt
    0.07
    Activations Density 0.023%

    No Known Activations