© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12986
    Prev
    Next
    INDEX
    Explanations

    اخت

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     democrat
    -0.08
     upright
    -0.08
     visc
    -0.08
     Indo
    -0.08
     Fö
    -0.08
     skepticism
    -0.07
    <v
    -0.07
    Ro
    -0.07
     Ro
    -0.07
     जांच
    -0.07
    POSITIVE LOGITS
    نا
    0.08
    咪
    0.07
     Mun
    0.07
     चाह
    0.07
     nur
    0.07
     المجالات
    0.07
    🏼
    0.07
     داده
    0.07
     مت
    0.07
    ideen
    0.07
    Activations Density 0.001%

    No Known Activations