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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120231
    Prev
    Next
    INDEX
    Explanations

    quick

    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
     blooming
    -0.09
    וצאות
    -0.08
    /community
    -0.08
    真的吗
    -0.08
    શ
    -0.08
    andidate
    -0.08
     inund
    -0.07
    anno
    -0.07
    -0.07
     বিভাগের
    -0.07
    POSITIVE LOGITS
     cameo
    0.10
     reconnaissance
    0.08
    ened
    0.08
     vende
    0.08
    _SEQUENCE
    0.08
    jmp
    0.08
     subdued
    0.08
    git
    0.08
     सा
    0.08
    -paced
    0.08
    Activations Density 0.009%

    No Known Activations