© 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. 30179
    Prev
    Next
    INDEX
    Explanations

    32

    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
     Peng
    -0.08
     سما
    -0.08
     coined
    -0.08
    ศัพท์
    -0.08
     brainstorming
    -0.08
    พิ
    -0.08
     Dharma
    -0.08
    اگر
    -0.08
     Hewlett
    -0.08
    langsung
    -0.08
    POSITIVE LOGITS
     жел
    0.08
    219
    0.08
    _CORE
    0.08
    001
    0.07
    22
    0.07
    242
    0.07
    jour
    0.07
    elif
    0.07
     peripheral
    0.07
    wb
    0.07
    Activations Density 0.006%

    No Known Activations