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. 130455
    Prev
    Next
    INDEX
    Explanations

    Units of measurement

    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
     deliber
    -0.08
    reck
    -0.08
     grass
    -0.07
    stice
    -0.07
     Monet
    -0.07
     Bere
    -0.07
    Constant
    -0.07
    -0.07
    Observe
    -0.07
    Observ
    -0.07
    POSITIVE LOGITS
     (%)
    0.10
    ?|
    0.08
    :</
    0.08
    łada
    0.08
     ताल
    0.08
     zul
    0.08
    ать
    0.08
     såg
    0.08
     defending
    0.08
    ®
    0.08
    Activations Density 0.018%

    No Known Activations