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. 49164
    Prev
    Next
    INDEX
    Explanations

    Application

    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
    ಗಳು
    -0.08
    Exponent
    -0.07
    Numer
    -0.07
    (identity
    -0.07
    案
    -0.07
    ಬೆ
    -0.07
     formes
    -0.07
     muod
    -0.07
    Against
    -0.07
    Perform
    -0.07
    POSITIVE LOGITS
     aca
    0.09
     Interrupt
    0.08
     wn
    0.08
     accustomed
    0.08
     Acad
    0.08
    cei
    0.08
     Settings
    0.08
     привык
    0.07
     ʻ
    0.07
     раздраж
    0.07
    Activations Density 0.001%

    No Known Activations