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. 77436
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     gł
    -0.09
     бю
    -0.08
    ounded
    -0.08
    riad
    -0.08
    ​ច
    -0.08
    elling
    -0.07
    羞
    -0.07
    licher
    -0.07
     스포츠
    -0.07
    //↵//↵//
    -0.07
    POSITIVE LOGITS
     luego
    0.08
     dónde
    0.08
     estudio
    0.07
     Luego
    0.07
     quickly
    0.07
     Reyes
    0.07
     promptly
    0.07
     cuándo
    0.07
    -from
    0.07
     rápidamente
    0.07
    Activations Density 0.004%

    No Known Activations