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. 15-RESID-POST-AA
    6. 19344
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .SYSTEM
    -0.09
    ,System
    -0.08
    'ch
    -0.08
    'description
    -0.08
     percept
    -0.08
    ുകൾ
    -0.08
     leased
    -0.08
     систем
    -0.08
    ändert
    -0.08
    APPLICATION
    -0.08
    POSITIVE LOGITS
     Placeholder
    0.08
    การ
    0.08
    We
    0.08
    _in
    0.07
    07
    0.07
     正
    0.07
    าการ
    0.07
    NY
    0.07
     �
    0.07
    ради
    0.07
    Activations Density 0.002%

    No Known Activations