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. 120429
    Prev
    Next
    INDEX
    Explanations

    Dehydration/water removal

    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
    험
    -0.08
    Standing
    -0.07
    र्ण
    -0.07
    ởi
    -0.07
     retrieval
    -0.07
     metaphor
    -0.07
    뢰
    -0.07
     etern
    -0.07
     Endless
    -0.07
    hearted
    -0.07
    POSITIVE LOGITS
     removes
    0.11
     unwanted
    0.10
     পানি
    0.10
    掉
    0.10
     impurities
    0.10
     удалить
    0.10
     очист
    0.09
     enlever
    0.09
    hilangan
    0.09
    .remove
    0.09
    Activations Density 0.009%

    No Known Activations