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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68927
    Prev
    Next
    INDEX
    Explanations

    plus

    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
     particulate
    -0.08
     incident
    -0.08
     puertas
    -0.08
     caminos
    -0.07
     Microsystems
    -0.07
     beper
    -0.07
    �
    -0.07
     paths
    -0.07
     displays
    -0.07
     મન
    -0.07
    POSITIVE LOGITS
    等级
    0.09
    效率
    0.08
     Doesn't
    0.08
     COMPLETE
    0.08
     wysok
    0.08
     Stephanie
    0.08
    עה
    0.08
     Efficiency
    0.08
     louder
    0.08
    高
    0.08
    Activations Density 0.001%

    No Known Activations