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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 88061
    Prev
    Next
    INDEX
    Explanations

    dental health

    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
     irritation
    -0.10
    MAR
    -0.09
     बाल
    -0.09
    conte
    -0.09
    urniture
    -0.08
     irritated
    -0.08
     Drawable
    -0.08
    ాంటి
    -0.08
     съд
    -0.08
     decorative
    -0.08
    POSITIVE LOGITS
     Nieder
    0.08
    .pause
    0.07
    ensch
    0.07
     anaer
    0.07
     wann
    0.07
     pauses
    0.07
     Sall
    0.07
    argc
    0.07
     Powell
    0.07
     mulle
    0.07
    Activations Density 0.001%

    No Known Activations