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. 88078
    Prev
    Next
    INDEX
    Explanations

    Times of day

    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
     �
    -0.08
    есті
    -0.08
    ולט
    -0.07
     malt
    -0.07
    iði
    -0.07
     bas
    -0.07
    完善
    -0.07
    ക്ട
    -0.07
    حال
    -0.07
     XK
    -0.07
    POSITIVE LOGITS
    Ingred
    0.08
    -east
    0.08
     ингреди
    0.08
     ADR
    0.08
     onwards
    0.08
    /day
    0.08
    peg
    0.08
    Fav
    0.08
     цвета
    0.07
     Gust
    0.07
    Activations Density 0.028%

    No Known Activations