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

    Neuronpedia

    APICircuit 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. 60793
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    apor
    -0.08
     walkway
    -0.08
     BX
    -0.08
     snug
    -0.08
     crescente
    -0.08
     Weg
    -0.08
     confusing
    -0.08
     kalau
    -0.08
     tuck
    -0.07
     rap
    -0.07
    POSITIVE LOGITS
     beliefs
    0.10
     preconce
    0.10
     знания
    0.10
     belief
    0.10
     ज्ञान
    0.09
     knowledge
    0.09
    (training
    0.08
     conocimientos
    0.08
     priori
    0.08
     impulses
    0.08
    Activations Density 0.003%

    No Known Activations