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. 112162
    Prev
    Next
    INDEX
    Explanations

    cover

    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
    olithic
    -0.09
    מין
    -0.08
     thrust
    -0.08
    olith
    -0.08
     gedurende
    -0.08
     assust
    -0.08
     propulsion
    -0.08
    phan
    -0.08
    .criteria
    -0.07
    .gravity
    -0.07
    POSITIVE LOGITS
     rendition
    0.10
     Remix
    0.10
     remix
    0.10
     نسخة
    0.10
     версия
    0.10
     versiones
    0.10
     karaoke
    0.10
    Versions
    0.10
     versions
    0.10
     versão
    0.09
    Activations Density 0.034%

    No Known Activations