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. 43152
    Prev
    Next
    INDEX
    Explanations

    let

    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
    zend
    -0.09
    ,en
    -0.08
    .webdriver
    -0.08
    chau
    -0.08
    hets
    -0.08
    .ads
    -0.08
    ேர
    -0.08
     kenne
    -0.08
     lj
    -0.08
    -campus
    -0.08
    POSITIVE LOGITS
     مساحة
    0.08
     χω
    0.08
     space
    0.08
     ഒഴിവ
    0.08
     impending
    0.07
     يو
    0.07
     اجازه
    0.07
     യു
    0.07
     ري
    0.07
     attempts
    0.07
    Activations Density 0.000%

    No Known Activations