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. 43056
    Prev
    Next
    INDEX
    Explanations

    gamma-ray astronomy

    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
     Sujet
    -0.08
     Verkäufer
    -0.08
     Schaden
    -0.08
     Leben
    -0.08
    締
    -0.08
     Thing
    -0.07
     materiales
    -0.07
     સામ
    -0.07
     사회
    -0.07
    irka
    -0.07
    POSITIVE LOGITS
     flower
    0.10
    Flower
    0.10
    Fot
    0.09
    flower
    0.09
     Flower
    0.09
    Photography
    0.08
     Photography
    0.08
     asas
    0.08
     flowers
    0.08
     photography
    0.07
    Activations Density 0.000%

    No Known Activations