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. 113015
    Prev
    Next
    INDEX
    Explanations

    tax treaty

    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
    икалық
    -0.08
     virt
    -0.07
    _IMPL
    -0.07
    mist
    -0.07
    .Args
    -0.07
     草
    -0.07
    lady
    -0.07
     rassemble
    -0.07
    留言
    -0.07
    .Drawing
    -0.07
    POSITIVE LOGITS
     negotiations
    0.09
     arranged
    0.08
    "/></
    0.08
     disputes
    0.08
     agreements
    0.08
     acuerdos
    0.08
    "/>↵
    0.08
     अन्तर
    0.08
     maut
    0.08
     onderhand
    0.08
    Activations Density 0.004%

    No Known Activations