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. 42050
    Prev
    Next
    INDEX
    Explanations

    fog

    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
    大会
    -0.08
    uyện
    -0.08
    观看
    -0.08
     environ
    -0.07
     finals
    -0.07
     فع
    -0.07
     barr
    -0.07
    كلة
    -0.07
     Basketball
    -0.07
    credit
    -0.07
    POSITIVE LOGITS
    break
    0.09
     burst
    0.08
    Cet
    0.08
    Dots
    0.08
     bursts
    0.08
    lamp
    0.08
    Bur
    0.07
    _Dep
    0.07
    _lp
    0.07
     lyn
    0.07
    Activations Density 0.002%

    No Known Activations