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. 30013
    Prev
    Next
    INDEX
    Explanations

    Await

    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
     കേന്ദ്ര
    -0.09
    λαν
    -0.08
    .Row
    -0.08
    .Input
    -0.08
     klas
    -0.08
     ആത്മ
    -0.08
     lyn
    -0.08
    中心
    -0.08
     ingestion
    -0.07
     കൊണ്ട്
    -0.07
    POSITIVE LOGITS
     Hinweise
    0.08
     cherries
    0.08
    �
    0.08
     fiancé
    0.08
     cheesecake
    0.08
     Yorkers
    0.08
     விட்ட
    0.08
     mozz
    0.08
     tear
    0.07
     Pia
    0.07
    Activations Density 0.001%

    No Known Activations