Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11627
    Prev
    Next
    INDEX
    Explanations

    divide

    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
    DC
    -0.08
     DC
    -0.07
     Seren
    -0.07
    Ser
    -0.07
    _PH
    -0.07
    	p
    -0.07
    scape
    -0.07
    iku
    -0.07
    אות
    -0.07
     Gu
    -0.06
    POSITIVE LOGITS
    拆
    0.12
    .Split
    0.12
     divides
    0.12
     বিভ
    0.11
     വിഭ
    0.11
     ভাগ
    0.11
    _into
    0.11
     dividing
    0.11
     بندی
    0.10
     विभ
    0.10
    Activations Density 0.068%

    No Known Activations