© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 743
    Prev
    Next
    INDEX
    Explanations

    recipes and ingredients

    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
     Wide
    -0.08
     ويس
    -0.08
    宇
    -0.08
     tilted
    -0.07
    _generate
    -0.07
     houding
    -0.07
     atendimento
    -0.07
     centred
    -0.07
     soud
    -0.07
     Atendimento
    -0.07
    POSITIVE LOGITS
     substitutions
    0.08
    erezo
    0.08
     pasirink
    0.08
     Bowie
    0.08
     choix
    0.08
     elección
    0.08
    umi
    0.08
     pilihan
    0.08
    0.08
     brauch
    0.08
    Activations Density 0.005%
    No Known Activations