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. 67158
    Prev
    Next
    INDEX
    Explanations

    resource

    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
    urz
    -0.07
     domin
    -0.07
    부터
    -0.07
     επικ
    -0.07
     occupants
    -0.07
    ередко
    -0.07
     مال
    -0.07
     ''
    -0.07
     സമീപ
    -0.07
     zem
    -0.07
    POSITIVE LOGITS
     inhale
    0.09
    (Web
    0.08
    Ingredient
    0.08
     ngum
    0.08
     quantified
    0.08
     mofuta
    0.08
     ingrediente
    0.08
    สินค้า
    0.08
    бут
    0.08
    লাইন
    0.08
    Activations Density 0.002%

    No Known Activations