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. 109068
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    MA
    -0.08
     viability
    -0.08
     contag
    -0.08
    alt
    -0.08
    lation
    -0.07
    Ma
    -0.07
    TJ
    -0.07
    assets
    -0.07
    fire
    -0.07
    ourg
    -0.07
    POSITIVE LOGITS
     Combat
    0.09
     Lufthansa
    0.08
     vaqt
    0.08
     કો
    0.08
     normalt
    0.08
     Komment
    0.08
     Einkauf
    0.08
     Ее
    0.08
     reducido
    0.08
     Cabin
    0.08
    Activations Density 0.001%

    No Known Activations