© 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. 91279
    Prev
    Next
    INDEX
    Explanations

    action reaction

    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
     deviation
    -0.08
     deviations
    -0.08
    idur
    -0.08
     mixing
    -0.08
    Deviation
    -0.08
     wandering
    -0.07
     rushing
    -0.07
    ivariate
    -0.07
     vitamins
    -0.07
     freedom
    -0.07
    POSITIVE LOGITS
     reciproc
    0.10
     symmetrical
    0.10
     reciprocal
    0.09
     зерк
    0.09
     взаим
    0.09
     Recipro
    0.09
    �
    0.09
     Mirrors
    0.09
     mirrored
    0.09
    互
    0.09
    Activations Density 0.001%

    No Known Activations