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. 55953
    Prev
    Next
    INDEX
    Explanations

    drizzle

    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
     অ
    -0.07
    _FP
    -0.07
    �
    -0.07
     Runde
    -0.07
     membre
    -0.07
     encompass
    -0.07
    .res
    -0.07
     sciences
    -0.07
     Spawn
    -0.07
    DEP
    -0.07
    POSITIVE LOGITS
    โปร
    0.08
     caramel
    0.08
     شعر
    0.07
    坊
    0.07
     Plum
    0.07
     fotóg
    0.07
     الشعر
    0.07
     которыми
    0.07
    ौत
    0.07
    يده
    0.07
    Activations Density 0.002%

    No Known Activations