© 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. 129295
    Prev
    Next
    INDEX
    Explanations

    conflict resolution strategies

    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
     Proms
    -0.08
     Corse
    -0.08
    �
    -0.08
     könne
    -0.08
    comma
    -0.08
     Finale
    -0.08
    href
    -0.08
     чаш
    -0.07
    favicon
    -0.07
    撮
    -0.07
    POSITIVE LOGITS
    .ACC
    0.09
     procrast
    0.08
    (Enum
    0.08
     remet
    0.08
     ALTER
    0.08
    bear
    0.08
     shifting
    0.08
     responses
    0.07
     wield
    0.07
     INDEX
    0.07
    Activations Density 0.005%

    No Known Activations