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. 43325
    Prev
    Next
    INDEX
    Explanations

    period

    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
     influx
    -0.10
    ద్�
    -0.08
    Param
    -0.08
    ccess
    -0.07
    _sub
    -0.07
    param
    -0.07
    الس
    -0.07
     onboarding
    -0.07
    許
    -0.07
    Daemon
    -0.07
    POSITIVE LOGITS
     nummer
    0.08
     yil
    0.08
     Ple
    0.08
     отзыв
    0.08
     ale
    0.08
     affiche
    0.08
     класс
    0.08
     Tritur
    0.08
     mindst
    0.07
     lust
    0.07
    Activations Density 0.003%

    No Known Activations