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. 106184
    Prev
    Next
    INDEX
    Explanations

    infinity symbol

    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
    虽
    -0.09
    抗
    -0.08
     máxim
    -0.08
     ovaj
    -0.08
     maksimal
    -0.08
     Maxim
    -0.08
     zaz
    -0.07
     Lovely
    -0.07
     Mock
    -0.07
    钟
    -0.07
    POSITIVE LOGITS
     ascending
    0.09
     asc
    0.08
     islands
    0.08
    ાયત
    0.08
     limitations
    0.07
     ⇒
    0.07
     કરવા
    0.07
    achi
    0.07
    。また
    0.07
    nst
    0.07
    Activations Density 0.013%

    No Known Activations