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. 8698
    Prev
    Next
    INDEX
    Explanations

    alternative medicine/bible

    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
     implique
    -0.08
     cycles
    -0.08
     cycl
    -0.08
     Ferien
    -0.07
     gestes
    -0.07
     fibers
    -0.07
     rénovation
    -0.07
     majeur
    -0.07
     abonnement
    -0.07
    Habit
    -0.07
    POSITIVE LOGITS
    avos
    0.08
     kuro
    0.08
    grep
    0.08
     כך
    0.08
    jdk
    0.07
    							↵
    0.07
     изп
    0.07
     pesan
    0.07
    charset
    0.07
     beverage
    0.07
    Activations Density 0.000%

    No Known Activations