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. 76546
    Prev
    Next
    INDEX
    Explanations

    division

    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
    举
    -0.08
     Guinness
    -0.08
     geschaffen
    -0.08
     बावजूद
    -0.08
     misleading
    -0.08
     dans
    -0.07
    teil
    -0.07
    add
    -0.07
    vi
    -0.07
     commemor
    -0.07
    POSITIVE LOGITS
     yielding
    0.09
     المنزل
    0.09
     polynomial
    0.09
     manually
    0.09
     Tay
    0.08
     Polynomial
    0.08
     Agen
    0.08
     العربية
    0.08
     вруч
    0.08
    /manual
    0.07
    Activations Density 0.009%

    No Known Activations